INDEX

Explanations

proper nouns related to locations, organizations, and persons

oai_token-act-pair · gpt-3.5-turbo

keywords related to news media and reporting

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

 Conserv

-0.69

 Gors

-0.67

auna

-0.66

 Humane

-0.64

 Creatures

-0.64

useum

-0.61

Zoo

-0.60

FREE

-0.59

ipedia

-0.58

 Louie

-0.58

POSITIVE LOGITS

udeau

0.73

ĵĺ

0.72

å£«

0.72

ãĥ¯ãĥ³

0.67

£ı

0.66

pport

0.65

imore

0.65

leck

0.63

tails

0.62

incinn

0.60

Activations Density 0.442%

proper nouns related to locations, organizations, and persons

keywords related to news media and reporting

No Comments

No Known Activations