INDEX

Explanations

terms related to social interactions or participation in a community

oai_token-act-pair · gpt-3.5-turbo

references to engagement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tera

-0.66

uran

-0.65

olog

-0.63

ological

-0.63

 Sabha

-0.61

 bosses

-0.60

falls

-0.59

Origin

-0.59

kowski

-0.59

 lethal

-0.59

POSITIVE LOGITS

 engagement

1.04

agement

0.88

naire

0.81

 engaged

0.79

EMENT

0.78

 engagements

0.77

itures

0.73

ATURE

0.72

able

0.72

hips

0.71

Activations Density 0.010%

terms related to social interactions or participation in a community

references to engagement in various contexts

No Comments

No Known Activations