INDEX

Explanations

mentions of boycott-related terms, particularly regarding Israel

oai_token-act-pair · gpt-3.5-turbo

mentions and discussions related to boycotts, especially targeting Israeli products or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

uscript

-0.75

itialized

-0.66

 Upload

-0.64

erick

-0.64

imag

-0.64

swick

-0.62

esville

-0.61

 lear

-0.61

oan

-0.61

 Paddock

-0.60

POSITIVE LOGITS

 boycott

1.33

 divest

1.31

 boycot

1.24

cott

1.24

BDS

0.95

 solidarity

0.91

aliation

0.87

 activism

0.86

 campaigns

0.80

heid

0.79

Activations Density 0.045%

mentions of boycott-related terms, particularly regarding Israel

mentions and discussions related to boycotts, especially targeting Israeli products or entities

No Comments

No Known Activations