INDEX

Explanations

code snippets and keywords related to programming and data processing

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

code delimiters and structure

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

 Wikimedijinoj

-0.56

sizeCache

-0.55

)"),

-0.55

IndentedString

-0.54

djangoproject

-0.54

OptionsMenu

-0.51

CppCodeGen

-0.50

Tembelea

-0.48

verifyException

-0.48

Bibliograf

-0.46

POSITIVE LOGITS

SharedCtor

0.47

 Signalez

0.45

 RemoteException

0.36

itatem

0.36

 Kuala

0.35

 Darby

0.35

thâu

0.35

 minimise

0.35

 characterised

0.34

 Bucure

0.34

Activations Density 0.079%

code snippets and keywords related to programming and data processing

code delimiters and structure

No Comments

No Known Activations