INDEX

Explanations

date formats and representations

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

ſelves

-0.58

 ſch

-0.56

Datuak

-0.55

Eſ

-0.54

 themſelves

-0.54

ſelf

-0.53

MLLoader

-0.52

 ſche

-0.52

ArgumentParser

-0.51

 beſ

-0.50

POSITIVE LOGITS

Jeografia

0.54

 borboleta

0.39

DIPSETTING

0.36

Nationalité

0.36

 saites

0.34

 Administrativna

0.33

üglich

0.33

joi

0.32

EndGlobalSection

0.31

Halaman

0.31

Activations Density 0.005%

date formats and representations

<start_of_turn>user

No Comments

No Known Activations