INDEX

Explanations

mentions of boycotts

oai_token-act-pair · gpt-3.5-turbo

references to boycotts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ixed

-0.73

uscript

-0.71

ptroller

-0.66

iscal

-0.65

ocre

-0.65

ancial

-0.64

missions

-0.64

opter

-0.63

regulated

-0.62

ahime

-0.60

POSITIVE LOGITS

 boycott

1.29

 boycot

1.14

cott

0.98

 divest

0.86

wana

0.79

Õ

0.78

ï¸

0.75

halla

0.74

ãĤ´ãĥ³

0.73

aliation

0.71

Activations Density 0.005%

mentions of boycotts

references to boycotts

No Comments

No Known Activations