INDEX

Explanations

words related to psychological tendencies or inclinations

oai_token-act-pair · gpt-3.5-turbo

phrases that describe recurring behaviors or patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aban

-0.80

loo

-0.78

gur

-0.77

mberg

-0.75

ighth

-0.73

tein

-0.73

arer

-0.72

zman

-0.72

oho

-0.71

zek

-0.71

POSITIVE LOGITS

 toward

1.12

 towards

1.02

 tendency

1.01

 tendencies

0.97

 predis

0.83

 propensity

0.81

 behavior

0.80

 behaviour

0.80

 shift

0.79

 Towards

0.78

Activations Density 0.019%

words related to psychological tendencies or inclinations

phrases that describe recurring behaviors or patterns

No Comments

No Known Activations