INDEX

Explanations

proper nouns and titles

oai_token-act-pair · gpt-3.5-turbo

prominent nouns or titles in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

RIS

-0.51

FAR

-0.50

 reliably

-0.50

 ease

-0.49

 pane

-0.49

 recoil

-0.49

 haste

-0.48

chio

-0.48

VERTISEMENT

-0.47

xp

-0.46

POSITIVE LOGITS

odore

0.76

resa

0.76

withstanding

0.73

cellence

0.73

ablishment

0.71

tainment

0.69

Nob

0.64

bye

0.64

Bron

0.62

Doc

0.61

Activations Density 0.535%

proper nouns and titles

prominent nouns or titles in the text

No Comments

No Known Activations