INDEX

Explanations

repetitive phrases regarding processes or steps in a sequence

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

after each event

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

 houſe

-0.50

saraba

-0.46

 European

-0.41

 Houſe

-0.41

 laſt

-0.41

 Peace

-0.40

 Majefty

-0.38

 Conſ

-0.38

 accepter

-0.38

European

-0.38

POSITIVE LOGITS

 kasarigan

0.55

 tartalomajánló

0.52

afterEach

0.48

每一次

0.48

 Meksiku

0.48

ngdoc

0.46

rungsseite

0.46

每次

0.44

verwijspagina

0.43

ReusableCell

0.41

Activations Density 0.036%

repetitive phrases regarding processes or steps in a sequence

after each event

No Comments

No Known Activations