INDEX

Explanations

numerical values related to technical specifications

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

transQ

-0.68

 EconPapers

-0.66

aarrggbb

-0.63

postsleuth

-0.63

Personensuche

-0.59

AndEndTag

-0.59

 CanadaChoose

-0.57

 useAppContext

-0.56

 disambiguazione

-0.56

InitVars

-0.54

POSITIVE LOGITS

 Bailly

0.35

)++;

0.33

WithIOException

0.33

 prévention

0.33

ifel

0.32

 фести

0.31

fi

0.31

 Agnew

0.31

Auszeichnungen

0.30

 aapt

0.29

Activations Density 0.000%

numerical values related to technical specifications

<start_of_turn>user

No Comments

No Known Activations