INDEX

Explanations

instances of the word "enable" followed by a number indicating level of activation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "enable" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

boy

-0.83

den

-0.75

alian

-0.68

apest

-0.67

ĳå£«

-0.67

 Rite

-0.66

 Nose

-0.64

à©

-0.64

 Warcraft

-0.64

à¨

-0.62

POSITIVE LOGITS

ment

0.80

cially

0.77

ments

0.76

untarily

0.74

 interoper

0.73

iences

0.72

auga

0.72

ezvous

0.71

xton

0.71

Reviewer

0.70

Activations Density 0.018%

instances of the word "enable" followed by a number indicating level of activation

instances of the word "enable" and its variations

No Comments

No Known Activations