INDEX

Explanations

references to reading, reviews, and calls to action for more information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

WithIOException

-0.57

ynie

-0.57

glBegin

-0.56

CloseOperation

-0.56

enderror

-0.55

EndInit

-0.55

esgue

-0.51

 Schen

-0.51

 Warren

-0.51

ngOnInit

-0.49

POSITIVE LOGITS

 Penh

0.54

曖昧さ回避

0.53

Jîn

0.52

oglobulin

0.52

 chairs

0.51

phalt

0.51

ystis

0.50

 Stimme

0.50

OGND

0.49

 مرئيه

0.49

Activations Density 0.085%

references to reading, reviews, and calls to action for more information

No Comments

No Known Activations