INDEX

Explanations

texts enclosed by the word "Cont"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "cont" indicating potential content-related discussions or references

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

EStream

-0.95

ħĭ

-0.83

lihood

-0.80

terday

-0.78

STER

-0.77

OPLE

-0.75

UGE

-0.74

manship

-0.67

GBT

-0.67

WT

-0.66

POSITIVE LOGITS

ributed

1.24

ainment

1.19

ainers

1.19

rast

1.15

ribution

1.14

roversial

1.12

rary

1.09

ribute

1.07

acts

1.06

rovers

1.03

Activations Density 0.016%

texts enclosed by the word "Cont"

variations of the word "cont" indicating potential content-related discussions or references

No Comments

No Known Activations