INDEX

Explanations

details related to accessibility resources and services

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

closed captioning and hearing

np_acts-logits-general · gemini-2.0-flash

sign language and captions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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



-0.55

artifactId

-0.50

bbero

-0.50

//

-0.49

 PublicKey

-0.47

клопе

-0.47

 Hưng

-0.47

 Consciousness

-0.47

SaveChanges

-0.46

ByExample

-0.46

POSITIVE LOGITS

 sign

1.23

 Sign

1.19

 interpreting

1.11

Sign

1.07

 signing

1.01

 SIGN

1.00

 interpreters

0.97

 deaf

0.96

 interpreter

0.96

 caption

0.92

Activations Density 0.143%

details related to accessibility resources and services

closed captioning and hearing

sign language and captions

No Comments

No Known Activations