INDEX

Explanations

URLs mentioning specific locations

oai_token-act-pair · gpt-3.5-turbo

web-related URLs and coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ilda

-0.65

shire

-0.62

 ACTIONS

-0.62

tein

-0.60

 Skinner

-0.58

ishers

-0.56

AFTA

-0.56

ESA

-0.55

enment

-0.54

heit

-0.53

POSITIVE LOGITS

soDeliveryDate

0.60

eper

0.60

ï¸ı

0.60

Writer

0.59

 Unloaded

0.58

Lens

0.58

itars

0.56

unic

0.55

Plex

0.55

processing

0.53

Activations Density 1.240%

URLs mentioning specific locations

web-related URLs and coding elements

No Comments

No Known Activations