INDEX

Explanations

code-related terms and structures pertinent to resource handling in APIs

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

configuration delimiters

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

 utafitiHapana

-0.55

 IndexPath

-0.49

URLException

-0.46

tagext

-0.44

delwed

-0.43

futbolista

-0.40

 bivolt

-0.39

akei

-0.39

 auroit

-0.38

 погре

-0.38

POSITIVE LOGITS

 InputDecoration

0.50

ParallelGroup

0.50

 defaultstate

0.48

cessite

0.42

بوابة

0.42

rrggbb

0.41

 Италијани

0.40

 farinha

0.39

出版年

0.39

ließlich

0.38

Activations Density 0.001%

code-related terms and structures pertinent to resource handling in APIs

configuration delimiters

No Comments

No Known Activations