INDEX

Explanations

proper names or entities, such as people's names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

emale

-0.63

ãĥ¼ãĥĨ

-0.57

shapeshifter

-0.55

eteria

-0.54

arettes

-0.53

Interstitial

-0.52

-0.50

 circulate

-0.50

../

-0.50

ãĥ¼ãĥ³

-0.49

POSITIVE LOGITS

 GOODMAN

0.65

 Rice

0.61

 Reed

0.61

 Roberts

0.58

Hos

0.57

 Miller

0.57

 Foster

0.56

 Butler

0.56

 Jenkins

0.56

 Bradley

0.56

Activations Density 0.476%

proper names or entities, such as people's names

proper nouns, specifically names of people

No Comments

No Known Activations