INDEX

Explanations

names and details of specific individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names associated with individuals or 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

 disposable

-0.56

 behav

-0.56

 conformity

-0.53

 favourable

-0.53

 conduc

-0.48

vap

-0.48

Tokens

-0.47

 triv

-0.47

 craving

-0.46

'."

-0.46

POSITIVE LOGITS

itars

0.63

anky

0.59

itone

0.58

acus

0.53

cussion

0.53

igl

0.52

endon

0.51

 Managing

0.51

jon

0.50

 Photographer

0.49

Activations Density 1.295%

names and details of specific individuals

proper nouns and names associated with individuals or entities

No Comments

No Known Activations