INDEX

Explanations

mentions of disabilities and related terms

oai_token-act-pair · gpt-3.5-turbo

references to disabilities

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

furt

-0.77

orically

-0.77

tons

-0.74

kov

-0.73

ãĥĥãĥĪ

-0.73

unin

-0.71

 ellipt

-0.70

ebus

-0.70

achus

-0.68

anza

-0.68

POSITIVE LOGITS

 disabilities

0.98

 disability

0.98

 Disability

0.96

 Disabled

0.81

 impair

0.79

 Rights

0.77

rights

0.76

 diagnoses

0.74

 Discrimination

0.73

afe

0.71

Activations Density 0.034%

mentions of disabilities and related terms

references to disabilities

No Comments

No Known Activations