INDEX

Explanations

phrases related to repeated actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

references to "habits" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ramid

-0.82

ammy

-0.80

SAR

-0.77

cross

-0.72

RIS

-0.71

govtrack

-0.66

merce

-0.65

stretched

-0.63

angered

-0.63

 GOODMAN

-0.62

POSITIVE LOGITS

 habit

1.37

 habits

1.07

uated

1.03

ually

0.97

uate

0.95

uation

0.89

uates

0.87

uating

0.77

 droid

0.71

ierre

0.69

Activations Density 0.004%

phrases related to repeated actions or behaviors

references to "habits" in various contexts

No Comments

No Known Activations