INDEX

Explanations

words related to oppression or suppression

oai_token-act-pair · gpt-3.5-turbo

expressions of suppression or negative sentiments regarding freedom

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Stars

-0.64

Ore

-0.61

 Ceres

-0.60

whe

-0.60

igmatic

-0.59

leaf

-0.59

 Hale

-0.59

CMS

-0.58

bright

-0.57

ready

-0.56

POSITIVE LOGITS

ategory

0.92

terness

0.88

elist

0.85

wart

0.84

hovah

0.83

utsche

0.79

ofi

0.75

nesses

0.74

 disadvant

0.74

SPONSORED

0.71

Activations Density 0.143%

words related to oppression or suppression

expressions of suppression or negative sentiments regarding freedom

No Known Activations