INDEX

Explanations

the word "me" in sentences

oai_token-act-pair · gpt-3.5-turbo

phrases indicating actions or events involving multiple subjects or objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

•Induction Feature

No Comments

Negative Logits

ãĥĩãĤ£

-0.86

ãĤ§

-0.70

ãĥĥ

-0.63

bryce

-0.59

avery

-0.58

cker

-0.58

ope

-0.56

sight

-0.56

ĨĴ

-0.56

 Howe

-0.56

POSITIVE LOGITS

in

1.13

in

1.06

IN

0.95

inen

0.86

 therein

0.82

In

0.81

In

0.80

 inside

0.75

edIn

0.73

lda

0.73

Activations Density 0.263%

the word "me" in sentences

phrases indicating actions or events involving multiple subjects or objects

No Comments

No Known Activations