INDEX

Explanations

words related to emotions, particularly anger

oai_token-act-pair · gpt-3.5-turbo

words associated with feelings of anger or related emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•layer 5 - anger

No Comments

Negative Logits

©¶æ

-1.04

eah

-0.93

©¶æ¥µ

-0.91

prus

-0.85

ichick

-0.83

İĭ

-0.79

ithing

-0.78

estinal

-0.78

cling

-0.78

cled

-0.74

POSITIVE LOGITS

ously

1.10

ous

1.00

OUS

0.86

xual

0.85

anger

0.79

 Jinn

0.71

ishly

0.70

azine

0.69

oes

0.67

deen

0.66

Activations Density 0.021%

words related to emotions, particularly anger

words associated with feelings of anger or related emotions

No Comments

No Known Activations