INDEX

Explanations

mentions of physical attributes or features of electronic devices

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

possessive pronouns indicating ownership or association

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

herty

-0.88

uminati

-0.76

itaire

-0.73

jac

-0.72

heim

-0.72

isson

-0.72

opsis

-0.70

naissance

-0.69

isky

-0.69

atis

-0.69

POSITIVE LOGITS

 predecessors

1.78

 counterparts

1.65

 predecessor

1.60

 peers

1.55

 contemporaries

1.49

 brethren

1.46

 counterpart

1.41

 rivals

1.39

 competitors

1.37

 predec

1.36

Activations Density 0.159%

mentions of physical attributes or features of electronic devices

possessive pronouns indicating ownership or association

No Comments

No Known Activations