INDEX

Explanations

expressions indicating a significant symbol or indication

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "sign" in various contexts suggesting an indication or implication of something

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

ĸļ

-0.75

ETHOD

-0.69

 Layer

-0.69

ategory

-0.63

 Remastered

-0.63

»Ĵ

-0.63

 Beans

-0.62

 DRAG

-0.60

ooked

-0.60

@#&

-0.60

POSITIVE LOGITS

atories

1.36

posts

1.15

ifying

1.09

atory

1.08

ifier

1.07

ifiers

1.02

alled

0.96

ific

0.96

 sign

0.95

ificantly

0.95

Activations Density 0.021%

expressions indicating a significant symbol or indication

occurrences of the word "sign" in various contexts suggesting an indication or implication of something

No Comments

No Known Activations