INDEX

Explanations

instances of the word "angry" or emotionally charged words and phrases related to anger

oai_token-act-pair · gpt-3.5-turbo

expressions of anger or frustration

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

sites

-0.97

uchin

-0.85

artifacts

-0.84

ingen

-0.83

akeru

-0.82

fman

-0.82

ajo

-0.81

icrobial

-0.81

glas

-0.81

 livest

-0.80

POSITIVE LOGITS

 outburst

0.95

 angry

0.90

 mobs

0.87

 parting

0.79

 indignation

0.79

 Birds

0.77

 shouts

0.76

 streak

0.74

 Angry

0.73

 anger

0.73

Activations Density 0.033%

instances of the word "angry" or emotionally charged words and phrases related to anger

expressions of anger or frustration

No Comments

No Known Activations