INDEX

Explanations

phrases questioning or emphasizing a point

oai_token-act-pair · gpt-3.5-turbo

phrases that prompt agreement or affirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

aples

-0.63

irlf

-0.63

 abroad

-0.62

icipated

-0.60

 Cosponsors

-0.59

etheus

-0.59

ufact

-0.59

ãĢĳ

-0.57

ternity

-0.54

theless

-0.54

POSITIVE LOGITS

1.24

?!

1.20

?).

1.12

!?

1.12

?"

1.11

?)

1.08

??

1.07

?),

1.04

?!"

1.03

.?

1.02

Activations Density 0.114%

phrases questioning or emphasizing a point

phrases that prompt agreement or affirmation

No Comments

No Known Activations