INDEX

Explanations

phrases starting with "urs" which might be related to medical terms or specific references

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "urs" and its variations, indicating a focus on legal or regulatory contexts related to personal rights or grievances

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Clarkson

-0.76

 Schn

-0.70

vantage

-0.64

 Butcher

-0.64

 Breaker

-0.63

 Tiff

-0.62

 Cobb

-0.62

 Slater

-0.62

 squared

-0.62

 Kingston

-0.61

POSITIVE LOGITS

hip

1.19

 confir

1.12

uits

1.05

uit

1.03

geons

1.02

urs

1.01

rences

0.93

olars

0.92

cript

0.90

itized

0.90

Activations Density 0.015%

phrases starting with "urs" which might be related to medical terms or specific references

occurrences of the term "urs" and its variations, indicating a focus on legal or regulatory contexts related to personal rights or grievances

No Comments

No Known Activations