INDEX

Explanations

medical terms and related words

oai_token-act-pair · gpt-3.5-turbo

references to medical personnel or medical themes

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

 Parish

-0.81

 Spear

-0.76

 Rend

-0.73

hyde

-0.73

 Mine

-0.72

Roe

-0.71

 Club

-0.70

 Swords

-0.70

nces

-0.70

 Accountability

-0.69

POSITIVE LOGITS

ented

0.96

sb

0.95

icip

0.94

ulates

0.94

itating

0.92

ilit

0.91

ript

0.90

ulators

0.89

itated

0.88

amb

0.87

Activations Density 0.053%

medical terms and related words

references to medical personnel or medical themes

No Comments

No Known Activations