INDEX

Explanations

proper nouns related to various individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

-0.78

 ..."

-0.70

[&

-0.64

ãĥīãĥ©

-0.63

 âĢ¦"

-0.62

Interstitial

-0.61

ãģ¾

-0.60

Untitled

-0.59

VOL

-0.58

AppData

-0.57

POSITIVE LOGITS

hower

1.00

sonian

0.83

anyahu

0.83

anwhile

0.75

espie

0.75

ashtra

0.74

ierrez

0.73

kefeller

0.72

endish

0.72

cair

0.71

Activations Density 0.200%

proper nouns related to various individuals

proper nouns or names within the text

No Comments

No Known Activations