INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

words with the suffix "ed" indicating past actions or conditions

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

SPONSORED

-0.62

å¥³

-0.62

 Bleach

-0.62

 whats

-0.61

 sans

-0.59

 DRAG

-0.55

 Britt

-0.54

 AUTHOR

-0.53

WHY

-0.53

 Luxembourg

-0.52

POSITIVE LOGITS

dit

1.38

ragon

1.31

uct

1.28

nesday

1.26

irect

1.23

rive

1.21

ict

1.19

iction

1.17

aily

1.16

ieval

1.16

Activations Density 0.125%

proper nouns

words with the suffix "ed" indicating past actions or conditions

No Comments

No Known Activations