INDEX

Explanations

mentions of various forms of disabilities

oai_token-act-pair · gpt-3.5-turbo

references to disabilities and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

furt

-0.89

 Collider

-0.76

kov

-0.73

orically

-0.72

 ellipt

-0.70

anza

-0.68

tons

-0.66

ãĥĥãĥĪ

-0.66

andum

-0.65

 Vald

-0.64

POSITIVE LOGITS

 disabilities

0.96

 disability

0.92

 Disability

0.89

 impair

0.85

 Disabled

0.78

onge

0.75

 diagnoses

0.74

abled

0.73

 cripp

0.71

 disabled

0.71

Activations Density 0.044%

mentions of various forms of disabilities

references to disabilities and related terms

No Comments

No Known Activations