INDEX

Explanations

proper nouns, likely related to significant events, places, or organizations

oai_token-act-pair · gpt-3.5-turbo

references to specific events, locations, or notable entities

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

blogs

-0.56

tem

-0.56

à¨

-0.55

brew

-0.55

 Samar

-0.53

pmwiki

-0.50

oret

-0.49

hor

-0.48

Nar

-0.48

ometric

-0.45

POSITIVE LOGITS

 ç¥ŀ

0.64

*.

0.61

robe

0.57

enium

0.56

ibia

0.55

ĸļ

0.55

iatus

0.55

ensis

0.54

 onwards

0.52

eers

0.52

Activations Density 0.919%

proper nouns, likely related to significant events, places, or organizations

references to specific events, locations, or notable entities

No Comments

No Known Activations