INDEX

Explanations

references to software configurations and algorithm specifications

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

driver, algorithm, adapter, engine, protocol

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

UnusedPrivate

-0.62

RegressionTest

-0.50

exitRule

-0.50

WebElementEntity

-0.48

 queſta

-0.47

Parcelize

-0.46

setVerticalGroup

-0.46

transQ

-0.45

parsedMessage

-0.44

 undef

-0.44

POSITIVE LOGITS

methoden

0.52

RunWith

0.50

method

0.48

getMethod

0.47

 methods

0.46

methods

0.45

 method

0.44

Географиясе

0.44

 выбран

0.43

choice

0.42

Activations Density 0.051%

references to software configurations and algorithm specifications

driver, algorithm, adapter, engine, protocol

No Comments

No Known Activations