INDEX

Explanations

references to code constructs and documentation

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

documentation and licenses

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

-0.40

 betweenstory

-0.39

 wszyst

-0.39

서

-0.38

 muž

-0.37

énération

-0.36

serviceWorker

-0.36

 pungkasnya

-0.36

LookAnd

-0.35

 pungkas

-0.35

POSITIVE LOGITS

tagHelperRunner

0.71

 MainAxisSize

0.60

 CURLOPT

0.55

 validamos

0.54

Tikang

0.53

хьтан

0.52

 disambiguazione

0.51

Carriera

0.50

AddTagHelper

0.49

columnNumber

0.48

Activations Density 0.001%

references to code constructs and documentation

documentation and licenses

No Comments

No Known Activations