INDEX

Explanations

punctuation marks and symbols indicating lists or sections

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

news and company names

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

oplayer

-0.60

 uſed

-0.58

endphp

-0.58

 resourceCulture

-0.57

 queſta

-0.57

 mijne

-0.56

 faſt

-0.54

lapsingToolbar

-0.54

новништво

-0.53

 jsPsych

-0.52

POSITIVE LOGITS

ñores

0.55



0.41

 Conley

0.38

而

0.38

Aholisi

0.38

Aviso

0.36

 Innenstadt

0.36

 Abends

0.36

省市镇

0.36

 міста

0.35

Activations Density 0.000%

punctuation marks and symbols indicating lists or sections

news and company names

No Comments

No Known Activations