INDEX

Explanations

words related to social interactions or behaviors

oai_token-act-pair · gpt-3.5-turbo

terms related to social behavior

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

nces

-0.84

atche

-0.79

xual

-0.75

ilts

-0.74

gran

-0.72

-0.71

ras

-0.70

gger

-0.70

shall

-0.70

oning

-0.69

POSITIVE LOGITS

 norms

0.96

 interaction

0.95

 interactions

0.95

 cues

0.89

ized

0.84

 relations

0.82

 gatherings

0.81

izing

0.78

istic

0.77

 affili

0.77

Activations Density 0.025%

words related to social interactions or behaviors

terms related to social behavior

No Comments

No Known Activations