INDEX

Explanations

terms related to programming and file types

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

technical terms and code elements

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

GraphicsUnit

-0.41

MenuView

-0.39

 Donahue

-0.36

 financieras

-0.36

Maße

-0.35

ChildScrollView

-0.35

 sufrido

-0.35

Ulm

-0.35

Ehrungen

-0.35

 onData

-0.35

POSITIVE LOGITS

mapbox

2.22

 disambiguazione

0.57

migrationBuilder

0.55

Parcelize

0.52

ulemon

0.52

enciaga

0.51

 lenker

0.50

ConstraintMaker

0.48

󠁮

0.47

Tikang

0.47

Activations Density 0.002%

terms related to programming and file types

technical terms and code elements

No Comments

No Known Activations