INDEX

Explanations

statistical terms and concepts related to structuring data or experimental results

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

mathematical or 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

RTEE

-0.55

 pinulongan

-0.51

.*")]

-0.50

 ExecuteAsync

-0.50

webElement

-0.49

XmlAccessType

-0.48

LookAnd

-0.47

jTable

-0.47

줬

-0.47

 بيها

-0.47

POSITIVE LOGITS

 Wikimedijinoj

0.49

parsedMessage

0.42

IndentedString

0.42

AccessorTable

0.41

@[+][

0.40

FieldBuilder

0.40

økt

0.37

MockBean

0.36

Izvori

0.35

ToAction

0.35

Activations Density 0.053%

statistical terms and concepts related to structuring data or experimental results

mathematical or technical terms

No Comments

No Known Activations