INDEX

Explanations

mentions of specific groups of people, specifically men and women

oai_token-act-pair · gpt-3.5-turbo

references to men and women in various contexts

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

Berry

-0.68

Prev

-0.68

IVERS

-0.68

REDACTED

-0.66

 Annex

-0.63

Closure

-0.63

DATA

-0.60

KEN

-0.60

ENC

-0.59

Main

-0.59

POSITIVE LOGITS

opausal

1.46

aces

1.35

orah

1.32

aced

1.27

volent

1.27

ager

1.22

endez

1.18

agers

1.09

folk

1.08

ial

1.03

Activations Density 0.063%

mentions of specific groups of people, specifically men and women

references to men and women in various contexts

No Comments

No Known Activations