INDEX

Explanations

references to well-known or notorious individuals, characters, or entities

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

famous or iconic things

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

 preſent

-0.50

 purpoſe

-0.50

 Reſ

-0.49

 cauſe

-0.47

 chrétiens

-0.46

 juſ

-0.46

 eſt

-0.44

 Perſ

-0.44

 Conſ

-0.43

 diſt

-0.42

POSITIVE LOGITS

 infamous

0.86

SourceChecksum

0.80

 famous

0.73

 notorious

0.73

famous

0.69

ніципа

0.69

 знамени

0.67

 famed

0.67

 dreaded

0.67

 famously

0.66

Activations Density 0.018%

references to well-known or notorious individuals, characters, or entities

famous or iconic things

No Comments

No Known Activations