INDEX

Explanations

namespaces and library references in programming code

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

namespace, class, function definitions

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

<bos>

-0.62

 Paglinawan

-0.51

 EnglishChoose

-0.47

saraba

-0.43

 iNdEx

-0.42

{:.

-0.42

 christlichen

-0.40

 चीज़ों

-0.39

पया

-0.39

MLLoader

-0.39

POSITIVE LOGITS

PerformLayout

0.54

expandindo

0.50

*)&

0.49

 automobiles

0.47

 Genetics

0.46

határoz

0.46

}{*}{}

0.45

 virtu

0.44

Rot

0.44

cestry

0.44

Activations Density 0.001%

namespaces and library references in programming code

namespace, class, function definitions

No Comments

No Known Activations