INDEX

Explanations

comparisons using the word "like"

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "like."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

cial

-0.60

reen

-0.55

igh

-0.55

aband

-0.54

elight

-0.52

hered

-0.52

lia

-0.51

cific

-0.51

ischer

-0.51

udic

-0.48

POSITIVE LOGITS

 that

1.46

 THAT

1.43

that

1.35

That

1.31

 That

1.19

 thats

1.05

 this

0.88

 those

0.71

Sounds

0.66

 THIS

0.65

Activations Density 0.932%

comparisons using the word "like"

phrases that include the word "like."

No Comments

No Known Activations