INDEX

Explanations

names of public figures, specifically female names

oai_token-act-pair · gpt-3.5-turbo

the names of specific individuals, particularly women

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

unin

-0.84

*/(

-0.79

culosis

-0.79

hire

-0.75

nation

-0.74

shit

-0.72

omatic

-0.71

ioch

-0.70

awar

-0.70

umbn

-0.69

POSITIVE LOGITS

Mae

1.12

 DeVos

1.08

 Louise

1.06

 Marie

1.04

 Lynn

1.04

 Jane

0.98

 Anne

0.95

 Nicole

0.93

 Patricia

0.93

Marie

0.92

Activations Density 0.080%

names of public figures, specifically female names

the names of specific individuals, particularly women

No Comments

No Known Activations