INDEX

Explanations

programming-related comments or documentation lines

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

Hentet

-0.74

 فريبيس

-0.72

 defStyle

-0.72

 ddelweddau

-0.68

 snippetHide

-0.66

fromnode

-0.65

DOCTYPE

-0.65

Initializable

-0.62

 الحره

-0.61

 jScrollPane

-0.59

POSITIVE LOGITS

uxxxx

0.64

 even

0.55

 Sedangkan

0.52

 ولك

0.50

TestTools

0.49

the

0.48

Nuorodos

0.46

家

0.46

>--}}

0.46

 while

0.46

Activations Density 0.227%

programming-related comments or documentation lines

No Comments

No Known Activations