INDEX

Explanations

comments and documentation within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glEnd

-0.73

URLException

-0.70

uarts

-0.68

parsedMessage

-0.68

createServer

-0.63

iNdEx

-0.61

ArgumentParser

-0.60

 awakeFromNib

-0.60

principalTable

-0.59

 FormsModule

-0.59

POSITIVE LOGITS

脚注の使い方

0.63

owanego

0.53

oa̍t

0.52

 hago

0.50

enumi

0.50

insane

0.49

 Daha

0.49

///

0.49

mine

0.48

 guardia

0.47

Activations Density 0.562%

comments and documentation within code

No Comments

No Known Activations