INDEX

Explanations

hyphenated phrases indicating the ranking or importance of something

oai_token-act-pair · gpt-3.5-turbo

ordinal rankings or positions in comparisons

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

EStream

-0.68

EMENT

-0.62

 curls

-0.61

 mirrors

-0.60

 sockets

-0.59

 Tune

-0.59

Cah

-0.58

 cups

-0.57

 Richards

-0.57

 Robertson

-0.57

POSITIVE LOGITS

highest

1.38

largest

1.38

ranked

1.34

favorite

1.30

generation

1.24

worst

1.24

best

1.18

ranking

1.17

degree

1.15

tier

1.14

Activations Density 0.031%

hyphenated phrases indicating the ranking or importance of something

ordinal rankings or positions in comparisons

No Comments

No Known Activations