INDEX

Explanations

intensifiers related to positive evaluations

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

super followed by an adjective

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

ตร์

-0.32

 onStop

-0.30

Voci

-0.29

 annonces

-0.29

 zune

-0.29

 Parlement

-0.28

vru

-0.27

Retirement

-0.26

 对象

-0.26

ituaries

-0.26

POSITIVE LOGITS

 super

1.02

 SUPER

0.93

 súper

0.91

super

0.80

SUPER

0.80

 супер

0.80

 awesome

0.78

Super

0.76

 incredibly

0.75

 veldig

0.73

Activations Density 0.004%

intensifiers related to positive evaluations

super followed by an adjective

No Comments

No Known Activations