INDEX

Explanations

phrases expressing significant occurrences or events

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

something happened

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

脚注の使い方

-0.54

 שוליים

-0.47

 endwhile

-0.43

 سكانية

-0.42

Vit

-0.41

ELTS

-0.41

CrossRef

-0.41

correct

-0.40

phyr

-0.39

 excesses

-0.39

POSITIVE LOGITS

 resourceCulture

0.45

 ujednoznacz

0.43

 disambiguazione

0.43

 Something

0.42

 tartalomajánló

0.38

 المعيارى

0.38

 ExecuteAsync

0.37

دانشنامهٔ

0.37

autorest

0.36

stateMutability

0.35

Activations Density 0.054%

phrases expressing significant occurrences or events

something happened

No Comments

No Known Activations