INDEX

Explanations

instances of legal terminology and references to regulations

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

Code or markup contextual characters

np_acts-logits-general · gemini-2.0-flash

Q and programmers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.95

 виправивши

-0.92

matchCondition

-0.83

verwijspagina

-0.79

RenderAtEndOf

-0.79

migrationBuilder

-0.79

antMatchers

-0.78

NameInMap

-0.78

^(@)

-0.78

DotNetBar

-0.77

POSITIVE LOGITS

0.49

zty

0.44

rove

0.42

激

0.41

大

0.41

烈

0.40

<sub>

0.40

enumi

0.40

icle

0.40

ob

0.40

Activations Density 0.175%

instances of legal terminology and references to regulations

Code or markup contextual characters

Q and programmers

No Comments

No Known Activations