INDEX

Explanations

references to specific programming concepts related to data types

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

<start_of_turn> user or nullable

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

новништво

-0.59

 confusión

-0.52

PerformLayout

-0.51

 imprese

-0.51

IsContent

-0.50

 confirmación

-0.50

 ilusión

-0.50

 composición

-0.49

 useStyles

-0.48

 adopción

-0.48

POSITIVE LOGITS

Nullable

1.28

MigrationBuilder

0.62

 Nullable

0.57

nullable

0.51

 nullable

0.50

AddTagHelper

0.43

viewWillAppear

0.40

TargetApi

0.39

GraphicsUnit

0.39

ChildScrollView

0.38

Activations Density 0.000%

references to specific programming concepts related to data types

<start_of_turn> user or nullable

No Comments

No Known Activations