INDEX

Explanations

technical terms and components related to programming and data handling

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

new control flow

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

QMetaType

-0.49

kuuta

-0.44

 Numerade

-0.41

Fall

-0.38

 Stur

-0.36

 fallu

-0.36

providedIn

-0.36

utilisons

-0.34

 שוליים

-0.34

AutoField

-0.34

POSITIVE LOGITS

StoryboardSegue

0.67

 AssemblyCulture

0.59

UrlResolution

0.58

(!__

0.53

الدراسه

0.48

jsonwebtoken

0.47

TProtocol

0.47

 useAppContext

0.46

 oprot

0.46

RegressionTest

0.45

Activations Density 0.244%

technical terms and components related to programming and data handling

new control flow

No Comments

No Known Activations