INDEX

Explanations

names of authors and reporters

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of individuals and authors

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.89

 Dame

-0.66

stood

-0.65

 comr

-0.63

 proport

-0.62

onement

-0.62

 receipts

-0.62

 undermin

-0.62

 pregn

-0.61

 discs

-0.61

POSITIVE LOGITS

(@

0.88

 Â·

0.84

cerpt

0.78

 Guest

0.78

ertodd

0.78

arth

0.78

 Contribut

0.76

iky

0.75

anan

0.75

maxwell

0.75

Activations Density 0.181%

names of authors and reporters

proper nouns, particularly names of individuals and authors

No Comments

No Known Activations