INDEX

Explanations

phrases related to instructions, guidelines, or specific actions

oai_token-act-pair · gpt-3.5-turbo

significant negative statements or critiques

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

Not in Any Lists

No Comments

Negative Logits

isms

-0.64

tty

-0.64

arium

-0.62

zing

-0.59

neau

-0.59

rop

-0.59

wolves

-0.58

cible

-0.56

abal

-0.56

ritic

-0.54

POSITIVE LOGITS

.","

0.84

.''

0.71

.ï¿½

0.71

\",

0.66

ãĢį

0.65

''.

0.65

.ãĢį

0.64

*/

0.64

.?

0.63

.",

0.63

Activations Density 1.734%

phrases related to instructions, guidelines, or specific actions

significant negative statements or critiques

No Comments

No Known Activations