INDEX

Explanations

words related to rules, regulations, and enforcement

oai_token-act-pair · gpt-3.5-turbo

references to rules and laws

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

itÃ©

-0.90

itate

-0.88

acters

-0.78

 Pradesh

-0.75

issance

-0.75

 Hots

-0.73

itant

-0.72

velength

-0.72

assador

-0.72

ity

-0.71

POSITIVE LOGITS

book

1.21

books

1.12

making

0.99

breaker

0.92

breakers

0.91

maker

0.89

makers

0.84

witz

0.81

lessness

0.80

 rule

0.77

Activations Density 0.021%

words related to rules, regulations, and enforcement

references to rules and laws

No Comments

No Known Activations