INDEX

Explanations

proper nouns, specifically names and titles

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

names followed by punctuation

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

ंदीखरीदारी

-0.93

MigrationBuilder

-0.88

 kaarangay

-0.87

 betweenstory

-0.84

SharedDtor

-0.82

adaptiveStyles

-0.82

 autorytatywna

-0.81

 BoxFit

-0.79

WireFormatLite

-0.79

 estekak

-0.76

POSITIVE LOGITS

0.44

0.41

0.39

0.38

↵

0.38

 Major

0.37

0.36

↵↵

0.35

Activations Density 0.017%

proper nouns, specifically names and titles

names followed by punctuation

No Comments

No Known Activations