INDEX

Explanations

references to the city of Berkeley

oai_token-act-pair · gpt-3.5-turbo

the name "Berkeley" mentioned repeatedly in various contexts

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

mble

-0.77

ugu

-0.77

oire

-0.77

ivably

-0.73

meaning

-0.71

ACTED

-0.68

 advoc

-0.66

orship

-0.66

 Cameroon

-0.63

istration

-0.63

POSITIVE LOGITS

keley

1.18

 Berkeley

0.90

 Heights

0.86

 Unified

0.86

shire

0.81

 Marina

0.81

 Extension

0.76

 County

0.74

 Hills

0.74

 Grounds

0.74

Activations Density 0.017%

references to the city of Berkeley

the name "Berkeley" mentioned repeatedly in various contexts

No Comments

No Known Activations