INDEX

Explanations

numerical information or lists

oai_token-act-pair · gpt-3.5-turbo

elements related to formatting and document structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Nev

-1.00

 Jericho

-0.89

 Clarks

-0.84

 Winchester

-0.81

 Merlin

-0.73

 Hartford

-0.73

 Lund

-0.73

 Sting

-0.71

 Greenwich

-0.71

 Stamford

-0.71

POSITIVE LOGITS

iston

0.89

0.82

ķ

0.75

catentry

0.74

0.73

ģĸ

0.73

Apr

0.72

interstitial

0.72

April

0.71

aye

0.71

Activations Density 0.106%

numerical information or lists

elements related to formatting and document structure

No Comments

No Known Activations