INDEX

Explanations

issues related to discrimination, harassment, and abuse

oai_token-act-pair · gpt-3.5-turbo

terms related to discrimination and its effects on various marginalized groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

clus

-0.63

dimension

-0.59

venue

-0.58

teness

-0.58

ILA

-0.56

Cal

-0.56

OPLE

-0.56

encer

-0.55

ACTED

-0.55

inois

-0.54

POSITIVE LOGITS

 owing

0.95

due

0.92

 stemming

0.89

 firsthand

0.84

 repercussions

0.84

 because

0.79

 ranging

0.78

 syndrome

0.76

 arising

0.76

 repr

0.75

Activations Density 0.258%

issues related to discrimination, harassment, and abuse

terms related to discrimination and its effects on various marginalized groups

No Comments

No Known Activations