INDEX

Explanations

code-related terms and instructions in programming contexts

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

// comments and code parameters

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

 HFILL

-0.59

CPtr

-0.57

posedge

-0.57

 MainAxisSize

-0.56

GOTREF

-0.56

principalColumn

-0.55

onOptions

-0.54

 MessageBoxIcon

-0.54

XmlIgnore

-0.53

AnchorStyles

-0.52

POSITIVE LOGITS

 Misalnya

0.38

demment

0.37

 Keuangan

0.36

íná

0.36

 Bidang

0.34

 utilice

0.33

 OFDb

0.33

 düş

0.33

 brightly

0.33

 skeletons

0.32

Activations Density 0.010%

code-related terms and instructions in programming contexts

// comments and code parameters

No Comments

No Known Activations