INDEX

Explanations

instances of the phrase "No" in various contexts, likely indicating legal case references or decisions

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

legal citations

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

RTCF

-0.63

 XCTest

-0.62

WireFormatLite

-0.60

AndEndTag

-0.57

Gambas

-0.56

Derbyniad

-0.56

fxml

-0.55

úgó

-0.55

tinyos

-0.55

лтемелер

-0.53

POSITIVE LOGITS

Padding

0.32

makeConstraints

0.30

Anmerkungen

0.29

 weakly

0.29

SequentialGroup

0.28

AnchorStyles

0.28

бята

0.28

Scrolled

0.28

 África

0.28

گز

0.27

Activations Density 0.001%

instances of the phrase "No" in various contexts, likely indicating legal case references or decisions

legal citations

No Comments

No Known Activations