INDEX

Explanations

terms related to user awareness and privacy concerns

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

self-

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 disambiguazione

-0.43

 invokingState

-0.40

SharedCtor

-0.38

RegressionTest

-0.37

tanleria

-0.36

 otomatig

-0.35

Coverage

-0.35

☚

-0.34

 manqué

-0.33

$_['

-0.32

POSITIVE LOGITS

 BorderSide

0.54

ftagPool

0.48

apunov

0.48

 rhestr

0.47

Rüyada

0.47

 intStringLen

0.46

 فريبيس

0.46

 getSystem

0.45

 NUKAT

0.44

enegal

0.43

Activations Density 0.002%

terms related to user awareness and privacy concerns

self-

No Comments

No Known Activations