INDEX

Explanations

mentions of people's occupations or roles

oai_token-act-pair · gpt-3.5-turbo

temporal indicators related to present and past states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

reth

-0.72

aceae

-0.71

stice

-0.71

rous

-0.69

xual

-0.68

onian

-0.68

arrow

-0.67

pled

-0.66

escal

-0.65

omical

-0.65

POSITIVE LOGITS

 residing

1.03

 known

0.95

 unemployed

0.94

 deceased

0.92

 retired

0.89

 employed

0.84

 aged

0.84

 stationed

0.84

 headed

0.82

 president

0.81

Activations Density 0.077%

mentions of people's occupations or roles

temporal indicators related to present and past states

No Comments

No Known Activations