INDEX

Explanations

mentions of men or males in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to males 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 @ 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

IVERS

-0.82

inventoryQuantity

-0.76

PsyNetMessage

-0.76

Regular

-0.73

veyard

-0.69

FW

-0.68

Daily

-0.68

Democratic

-0.68

icut

-0.66

IFT

-0.66

POSITIVE LOGITS

hunt

1.27

nered

1.18

uscript

1.13

hood

1.11

gling

0.98

volent

0.92

agers

0.89

ila

0.88

who

0.86

handled

0.86

Activations Density 0.044%

mentions of men or males in various contexts

references to males in various contexts

No Comments

No Known Activations