INDEX

Explanations

various punctuation marks and quotation forms

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

section boundary markers

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 فريبيس

-0.72

 صوتيه

-0.67

 الحره

-0.64

 oprot

-0.60

principalColumn

-0.60

saraba

-0.59

出版年

-0.59



-0.58

IsContent

-0.56

MemoryWarning

-0.55

POSITIVE LOGITS

 excerpt

0.50

 excerpts

0.48

excerpt

0.46

 extrait

0.44

extract

0.42

emphasis

0.41

cerpts

0.41

explanation

0.40

 summarizes

0.39

endregion

0.39

Activations Density 0.054%

various punctuation marks and quotation forms

section boundary markers

No Comments

No Known Activations