INDEX

Explanations

numerical identifiers or quantities related to various subjects

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

<start_of_turn> user

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

:✨

-0.88

 مواليد

-0.54

contentLoaded

-0.52

üyada

-0.48

ValueStyle

-0.44

 useAppContext

-0.42

 CURIAM

-0.42

 StatefulWidget

-0.40

GTCX

-0.39

nezeu

-0.39

POSITIVE LOGITS

IntoConstraints

0.47

glTexCoord

0.43

 random

0.43

征

0.41

脚注の使い方

0.41

ostringstream

0.40

 ervan

0.40

 resourceCulture

0.40

atil

0.39

findpost

0.39

Activations Density 0.000%

numerical identifiers or quantities related to various subjects

<start_of_turn> user

No Comments

No Known Activations

numerical identifiers or quantities related to various subjects

<start_of_turn> user

No Comments

No Known Activations