INDEX

Explanations

phrases related to setting fires or conflicts

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to fire, aggression, and conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Not in Any Lists

No Comments

Negative Logits

 Huntington

-0.71

 commute

-0.66

 cheat

-0.64

imeter

-0.63

 quint

-0.61

 lifetime

-0.59

 peas

-0.56

 towed

-0.56

 paid

-0.55

hoe

-0.55

POSITIVE LOGITS

EEE

0.75

actionDate

0.73

aciously

0.72

Â§

0.71

earances

0.70

Dialogue

0.70

Film

0.70

ãĥĢ

0.69

0.68

andise

0.66

Activations Density 0.159%

phrases related to setting fires or conflicts

words and phrases related to fire, aggression, and conflict

No Comments

No Known Activations