INDEX

Explanations

references to the concept of beginnings in various contexts

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

beginning of

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

acamata

-0.55

$_['

-0.48

 Toxicol

-0.42

arache

-0.42

ragamo

-0.42

 Vote

-0.41

voerd

-0.41

Sulf

-0.40

 Pollut

-0.40

nalpot

-0.40

POSITIVE LOGITS

beginning

1.20

 beginning

1.16

 Beginning

1.13

Beginning

1.09

 BEGINNING

1.06

 beginnings

0.92

 begins

0.91

 begin

0.90

 Beginnings

0.90

 começo

0.89

Activations Density 0.006%

references to the concept of beginnings in various contexts

beginning of

No Comments

No Known Activations