INDEX

Explanations

the word "spokeswoman" in news articles

oai_token-act-pair · gpt-3.5-turbo

references to spokespersons or spokesperson-related terminology

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

rament

-0.76

akespe

-0.66

vernment

-0.65

 insepar

-0.65

SPONSORED

-0.65

ozy

-0.63

 thirsty

-0.62

ypes

-0.62

undo

-0.62

usalem

-0.61

POSITIVE LOGITS

 Anne

1.04

 Marie

0.95

 Louise

0.94

Anne

0.94

 Nicole

0.93

 Maria

0.92

 Isabel

0.87

 Mary

0.87

 maid

0.84

cule

0.83

Activations Density 0.029%

the word "spokeswoman" in news articles

references to spokespersons or spokesperson-related terminology

No Known Activations