INDEX

Explanations

mentions of the city of Berkeley

oai_token-act-pair · gpt-3.5-turbo

references to the city of Berkeley

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ugu

-0.86

meaning

-0.71

oire

-0.70

mble

-0.66

ivably

-0.66

demand

-0.65

ollow

-0.64

ACTED

-0.63

BOOK

-0.63

orship

-0.63

POSITIVE LOGITS

keley

1.22

 Berkeley

1.02

shire

0.83

halla

0.79

 Unified

0.78

Nig

0.76

phrine

0.75

 Heights

0.74

 Extension

0.72

 Marina

0.70

Activations Density 0.006%

mentions of the city of Berkeley

references to the city of Berkeley

No Comments

No Known Activations