INDEX

Explanations

programming syntax and structure related to function calls and handling results

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

code 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

 protoimpl

-0.57

 InputDecoration

-0.51

 ivelany

-0.48

expandindo

-0.47

 iParam

-0.45

ंदीखरीदारी

-0.45

/**

-0.44

 paciencia

-0.44

EnableWeb

-0.44

InjectMocks

-0.44

POSITIVE LOGITS

oa̍t

0.48

richTextPanel

0.46

stätte

0.42

 outweigh

0.40

 Venti

0.40

 instrumentation

0.40

تج

0.39

 runt

0.39

GOTREF

0.39

Stdout

0.38

Activations Density 0.011%

programming syntax and structure related to function calls and handling results

code and technical terms

No Comments

No Known Activations