INDEX

Explanations

phrases related to disabilities

oai_token-act-pair · gpt-3.5-turbo

mentions of disabilities and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

anza

-0.79

 ellipt

-0.76

atorial

-0.71

ectar

-0.69

rams

-0.69

amy

-0.68

 Volt

-0.68

uri

-0.68

orically

-0.67

articles

-0.67

POSITIVE LOGITS

 disability

1.13

 Disability

1.07

 disabilities

0.95

 Disabled

0.82

 impair

0.77

 inval

0.77

 disabled

0.74

 unemploy

0.73

abled

0.72

 Leilan

0.71

Activations Density 0.007%

phrases related to disabilities

mentions of disabilities and related terminology

No Comments

No Known Activations