INDEX

Explanations

references to specific legal cases or commentary on legal interpretations

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

continued, table references

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

DoubleQuotes

-0.62

BrowserModule

-0.61

Hentet

-0.61

MigrationBuilder

-0.61

ConstraintMaker

-0.60

 BrowserModule

-0.58

 MainAxisSize

-0.57

出版年

-0.56

XmlAccessType

-0.56

 المعيارى

-0.55

POSITIVE LOGITS

//

0.39

 canlynol

0.35

<em>

0.35

 Trench

0.35



0.33

 Felton

0.32

↵↵↵

0.32

AK

0.32

/*

0.32

 gren

0.32

Activations Density 0.016%

references to specific legal cases or commentary on legal interpretations

continued, table references

No Comments

No Known Activations