INDEX

Explanations

negation statements or expressions indicating conditions that are not met

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

negation operator `!(`, `((`, `(\`

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

️

-0.52

">//

-0.51

Naval

-0.44

fortawesome

-0.43

AxisAlignment

-0.42

greenrobot

-0.41

{(-

-0.40

 незавершена

-0.40

 malos

-0.40

 onAnimation

-0.40

POSITIVE LOGITS

(!(

1.83

(!(

1.71

!(

1.28

!(

0.57

(!$

0.54

esez

0.53

 Instrum

0.52

 Infór

0.48

 rivol

0.47

abestanden

0.46

Activations Density 0.017%

negation statements or expressions indicating conditions that are not met

negation operator `!(`, `((`, `(\`

No Comments

No Known Activations