INDEX

Explanations

adjectives with negative connotations

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating disgust or negative sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 livest

-0.66

stadt

-0.64

 lapse

-0.62

 hypers

-0.60

Ô

-0.59

 smack

-0.58

arella

-0.58

 glut

-0.57

 hover

-0.57

aic

-0.55

POSITIVE LOGITS

owship

0.97

ointed

0.92

ption

0.87

akable

0.83

ivable

0.82

achment

0.81

ction

0.79

untled

0.79

atives

0.78

agement

0.78

Activations Density 0.053%

adjectives with negative connotations

words and phrases indicating disgust or negative sentiments

No Comments

No Known Activations