INDEX

Explanations

proper names of people

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals

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

Not in Any Lists

No Comments

Negative Logits

unin

-0.84

zees

-0.79

igo

-0.77

heimer

-0.76

nation

-0.74

direction

-0.73

hire

-0.73

etheus

-0.72

byter

-0.71

arak

-0.69

POSITIVE LOGITS

 Marie

1.08

 Lynn

1.03

 Patricia

1.00

Mae

0.97

Marie

0.96

 Borders

0.93

 Nicole

0.92

 Michelle

0.92

 Louise

0.91

 Anne

0.90

Activations Density 0.043%

proper names of people

proper nouns, particularly names of individuals

No Comments

No Known Activations