INDEX

Explanations

judgmental expressions indicating disapproval or criticism

oai_token-act-pair · gpt-3.5-turbo

instances of the word "hardly" indicating minimal impact or significance

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

ividual

-0.83

spin

-0.69

emy

-0.68

hang

-0.65

MAT

-0.65

runs

-0.64

iem

-0.64

alez

-0.64

yne

-0.63

eki

-0.61

POSITIVE LOGITS

 percept

0.84

 bother

0.78

 noticeable

0.73

 paralle

0.73

 bothered

0.72

 conceivable

0.72

 distinguish

0.71

withstanding

0.71

shy

0.69

 ever

0.69

Activations Density 0.018%

judgmental expressions indicating disapproval or criticism

instances of the word "hardly" indicating minimal impact or significance

No Comments

No Known Activations