INDEX

Explanations

references to awards and recognition in media or film contexts

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

Tokens appearing within parentheses

np_acts-logits-general · gemini-2.0-flash

dates and technical terms

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

 Exacts

-0.76

 Prato

-0.55

TagMode

-0.54

 Thirteenth

-0.53

jamientos

-0.53

 resourceCulture

-0.52

BRACKET

-0.50

obod

-0.49

(!__

-0.49

passphrase

-0.48

POSITIVE LOGITS

 مشين

0.65

WireFormatLite

0.56

LLocation

0.52

 nano

0.50

Билгалдахарш

0.50

 оригіналу

0.49

HandleFunc

0.49

textTheme

0.47

didSet

0.47

ObjectMeta

0.47

Activations Density 0.177%

references to awards and recognition in media or film contexts

Tokens appearing within parentheses

dates and technical terms

No Comments

No Known Activations