INDEX

Explanations

titles or headings of sections or articles

oai_token-act-pair · gpt-3.5-turbo

empty or placeholder content

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

stood

-0.70

Interstitial

-0.68

ilaterally

-0.67

emale

-0.65

xxxx

-0.59

_.

-0.57

milo

-0.56

akespe

-0.56

ä»£

-0.55

pheus

-0.55

POSITIVE LOGITS

zbollah

0.64

UTERS

0.60

Berry

0.60

chwitz

0.59

 largeDownload

0.58

hesda

0.57

 Mant

0.54

ANS

0.53

Elsa

0.53

buquerque

0.53

Activations Density 0.196%

titles or headings of sections or articles

empty or placeholder content

No Comments

No Known Activations