INDEX

Explanations

names of people or locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names within the text

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

Palest

-0.67

Ô

-0.66

©¶æ

-0.66

 exting

-0.66

Balt

-0.65

 Citiz

-0.64

VALUE

-0.63

 Azerbai

-0.63

VOL

-0.62

 gobl

-0.62

POSITIVE LOGITS

shire

1.02

icz

0.99

ieri

0.94

lli

0.90

ians

0.90

sson

0.88

Jr

0.88

ttes

0.88

idge

0.87

orld

0.86

Activations Density 0.239%

names of people or locations

proper nouns and names within the text

No Comments

No Known Activations