INDEX

Explanations

words related to transactions or interactions between individuals or entities

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or entities related to various themes

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

ï¸ı

-0.63

 partName

-0.61

 sshd

-0.59

 spoilers

-0.57

CHQ

-0.53

negie

-0.53

hiba

-0.53

}}}

-0.52

Brave

-0.52

enting

-0.52

POSITIVE LOGITS

swick

0.71

geist

0.70

arest

0.68

 compr

0.65

ames

0.62

 âĸº

0.60

rium

0.58

legate

0.57

lict

0.57

aku

0.56

Activations Density 0.179%

words related to transactions or interactions between individuals or entities

references to specific locations or entities related to various themes

No Comments

No Known Activations