INDEX

Explanations

people's names, specifically focusing on the word "Men"

oai_token-act-pair · gpt-3.5-turbo

the word "Men" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ENCY

-0.71

BLIC

-0.70

tainment

-0.65

ä½¿

-0.64

ITED

-0.64

âĺħâĺħ

-0.64

enance

-0.64

RAY

-0.63

VICE

-0.63

Closure

-0.63

POSITIVE LOGITS

endez

1.38

iscal

1.19

cius

1.04

ager

1.00

opausal

0.99

agogue

0.97

istries

0.94

uscript

0.93

ghai

0.92

omen

0.90

Activations Density 0.030%

people's names, specifically focusing on the word "Men"

the word "Men" in various contexts

No Comments

No Known Activations