INDEX

Explanations

structured data formats, specifically related to code or database entries involving names, IDs, and commands

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

programming code contexts

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

 onPostExecute

-0.43

 ProtoMessage

-0.39

 ritratto

-0.39

AddTagHelper

-0.38

 étro

-0.37

GraphicsUnit

-0.36

 saurait

-0.36

 contextLoads

-0.35

 esportivo

-0.33

 istrinya

-0.33

POSITIVE LOGITS

EDEFAULT

0.52

 defaultstate

0.50

ConverterFactory

0.50

 Regist

0.50

LabelTagHelper

0.50

WithIOException

0.47

ushi

0.47

ollectionView

0.46

GeneratedValue

0.45

AnchorTagHelper

0.45

Activations Density 0.012%

structured data formats, specifically related to code or database entries involving names, IDs, and commands

programming code contexts

No Comments

No Known Activations