INDEX

Explanations

references to villains in various contexts

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

villain or antagonist

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 المعيارى

-0.77

cotch

-0.57

PRS

-0.52

XmlAccessType

-0.51

 RestTemplate

-0.50

✱

-0.50

httphttps

-0.49

❊

-0.48

CFS

-0.47

Sper

-0.47

POSITIVE LOGITS

 villain

1.72

 villains

1.45

 Villain

1.45

villain

1.45

 antagonist

0.80

 ennemi

0.77

 enemy

0.75

 VILL

0.71

 vill

0.67

 héroe

0.66

Activations Density 0.004%

references to villains in various contexts

villain or antagonist

No Comments

No Known Activations

references to villains in various contexts

villain or antagonist

No Comments

No Known Activations