INDEX

Explanations

questions or inquiry-oriented phrases

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

ordering, <start_of_turn> user, clang

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

+#+#

-0.54

nocache

-0.51

 IMPLIED

-0.48

 NgModule

-0.42

EqualsAnd

-0.39

ftagPool

-0.38

 nahilalakip

-0.38

 blogs

-0.37

 abroad

-0.37

 intptr

-0.36

POSITIVE LOGITS

 pageable

0.59

MigrationBuilder

0.54

principalColumn

0.54

DockStyle

0.54

 ModelExpression

0.53

 FetchType

0.50

"]);

0.49

Zeneca

0.49

IVEREF

0.48

Carriera

0.48

Activations Density 0.000%

questions or inquiry-oriented phrases

ordering, <start_of_turn> user, clang

No Comments

No Known Activations