INDEX

Explanations

instances of time-related references and changes

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

now, then, new, provides

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

örgy

-0.48

Personensuche

-0.48

/*

-0.47

 leaders

-0.45

 autorytatywna

-0.43

//

-0.43

-0.41

%)$

-0.40

pushFollow

-0.40

 gern

-0.40

POSITIVE LOGITS

keyColumn

0.52

 Confirm

0.46

 <<<<<<<<<<<<<<

0.44

SourceChecksum

0.43

enterOuterAlt

0.43

now

0.43

 confirms

0.42

CONFIRM

0.41

 AssemblyTitle

0.41

 ModelExpression

0.41

Activations Density 0.052%

instances of time-related references and changes

now, then, new, provides

No Comments

No Known Activations