INDEX

Explanations

technical terms and concepts related to software and data processing

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

foreign and technical terms

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

 faſt

-0.47

 ſta

-0.44

 raiſ

-0.43

 deſt

-0.43

setVerticalGroup

-0.43

 beſ

-0.42

 ſch

-0.39

 Caster

-0.39

POSITIVE LOGITS

 للاسماء

0.49

 Мексичка

0.48

SharedCtor

0.46

IndentedString

0.45

 ujednoznacz

0.42

astéroïdes

0.40

 lenker

0.40

 فريبيس

0.39

Bioaccumulative

0.39

UnusedPrivate

0.39

Activations Density 0.288%

technical terms and concepts related to software and data processing

foreign and technical terms

No Comments

No Known Activations