INDEX

Explanations

text related to categorization and information organization

oai_token-act-pair · gpt-3.5-turbo

references to categories and themes in various submissions or posts

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

paces

-0.89

recy

-0.75

Reviewer

-0.70

staking

-0.70

cuts

-0.68

mbuds

-0.65

comings

-0.64

assi

-0.64

arde

-0.61

sie

-0.61

POSITIVE LOGITS

inion

0.61

 rapt

0.56

 chimpan

0.56

 grips

0.56

 dimension

0.55

 count

0.55

ixture

0.55

 caus

0.54

tee

0.54

 rank

0.53

Activations Density 0.255%

text related to categorization and information organization

references to categories and themes in various submissions or posts

No Comments

No Known Activations