INDEX

Explanations

words related to actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

words related to act and action-oriented concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 tradem

-0.83

yip

-0.82

Ń·

-0.81

 whisk

-0.78

ĨĴ

-0.75

 tremend

-0.74

psey

-0.72

uyomi

-0.71

awaru

-0.69

 flared

-0.69

POSITIVE LOGITS

act

1.16

uated

1.02

uary

0.96

ional

0.93

itol

0.86

ivism

0.86

Pub

0.85

ivity

0.83

uate

0.82

asia

0.79

Activations Density 0.009%

words related to actions or behaviors

words related to act and action-oriented concepts

No Comments

No Known Activations