INDEX

Explanations

verbs indicating action or change

oai_token-act-pair · gpt-3.5-turbo

variations of the word "also" and related quantifying adverbs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

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

yond

-0.66

etting

-0.65

Subject

-0.63

YING

-0.60

GROUND

-0.56

aq

-0.56

idding

-0.55

Rap

-0.55

 Digest

-0.55

 Carm

-0.54

POSITIVE LOGITS

been

1.60

 been

1.50

 undergone

1.28

 gotten

1.19

 Been

1.11

 become

1.10

 begun

1.09

 fallen

1.08

 gone

1.04

 come

1.00

Activations Density 0.154%

verbs indicating action or change

variations of the word "also" and related quantifying adverbs

No Comments

No Known Activations