INDEX

Explanations

verbs or phrases related to enabling or making something possible

oai_token-act-pair · gpt-3.5-turbo

usages of the word "enable" and its variations, indicating discussions about facilitation or capacity

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

apest

-0.89

boy

-0.77

ĳå£«

-0.73

 Nose

-0.67

worn

-0.67

thin

-0.66

antam

-0.65

anne

-0.65

ioxide

-0.65

numbered

-0.63

POSITIVE LOGITS

ment

0.86

ments

0.84

 interoper

0.79

us

0.75

iences

0.74

untarily

0.71

mentation

0.70

hift

0.70

auga

0.69

ezvous

0.68

Activations Density 0.029%

verbs or phrases related to enabling or making something possible

usages of the word "enable" and its variations, indicating discussions about facilitation or capacity

No Comments

No Known Activations