INDEX

Explanations

words related to changes, especially sudden or significant shifts

oai_token-act-pair · gpt-3.5-turbo

adverbs and expressions indicating frequency or occurrence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Digest

-0.59

GROUND

-0.58

 alive

-0.56

Subject

-0.54

 weap

-0.54

avier

-0.53

zing

-0.53

Reviewer

-0.53

SG

-0.53

etting

-0.52

POSITIVE LOGITS

been

1.75

 been

1.64

 gotten

1.41

 undergone

1.35

 begun

1.27

 Been

1.26

 fallen

1.25

 gone

1.19

 become

1.16

 risen

1.15

Activations Density 0.218%

words related to changes, especially sudden or significant shifts

adverbs and expressions indicating frequency or occurrence

No Comments

No Known Activations