INDEX

Explanations

acronyms and specific organization names

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

acronyms and abbreviations

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

 препратки

-0.42

Искәрмәләр

-0.39

AddTagHelper

-0.37

WriteAttribute

-0.37

matching

-0.36

legate

-0.36

وفاته

-0.36

 lecteur

-0.35

migrationBuilder

-0.35

 nejak

-0.35

POSITIVE LOGITS

styleable

0.43

WindowConstants

0.42

 otomatig

0.42

Datuak

0.41

ientôt

0.41

AnchorStyles

0.40

OGND

0.38

Nationalité

0.38

 виправивши

0.38

 Props

0.37

Activations Density 0.054%

acronyms and specific organization names

acronyms and abbreviations

No Comments

No Known Activations