INDEX

Explanations

words related to negative emotions, particularly focusing on the feeling of anger

oai_token-act-pair · gpt-3.5-turbo

expressions of anger

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

•layer 6 - anger

No Comments

Negative Logits

 Operator

-0.69

 Vide

-0.69

 Wonders

-0.66

artifacts

-0.66

 Places

-0.65

 snug

-0.63

 livest

-0.62

MER

-0.62

ramer

-0.61

amins

-0.61

POSITIVE LOGITS

fulness

1.03

ful

0.95

rained

0.94

FUL

0.88

ingly

0.86

wart

0.85

fully

0.82

lessness

0.82

lessly

0.82

 anger

0.80

Activations Density 0.046%

words related to negative emotions, particularly focusing on the feeling of anger

expressions of anger

No Comments

No Known Activations