INDEX

Explanations

adjectives and proper nouns

oai_token-act-pair · gpt-3.5-turbo

variations of the word "state" or related legal terminology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.83

enegger

-0.79

heit

-0.66

htaking

-0.65

 agitation

-0.65

 breathing

-0.64

gp

-0.63

hof

-0.63

Ou

-0.62

rat

-0.59

POSITIVE LOGITS

ulo

0.81

isions

0.80

Redd

0.75

inarily

0.75

Ģ

0.73

OTAL

0.73

acion

0.72

³

0.71

Ĩ

0.71

etary

0.70

Activations Density 0.322%

adjectives and proper nouns

variations of the word "state" or related legal terminology

No Comments

No Known Activations