INDEX

Explanations

specific names or terms related to corporations and their products

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

mathematical $\mathcal{V}$ expressions

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

WireFormatLite

-0.48

aarrggbb

-0.37

 Schließlich

-0.35

 незавершена

-0.35

 المعيارى

-0.34

 Bedürfnisse

-0.34

 następu

-0.34

ieważ

-0.33

 perfección

-0.33

POSITIVE LOGITS

PreInfinity

0.65

oredCriteria

0.52

 ISNI

0.52

MessageOf

0.51

emb

0.51

 HasFactory

0.50

Lec

0.49

 electrically

0.48

Planet

0.48

lanta

0.48

Activations Density 0.056%

specific names or terms related to corporations and their products

mathematical $\mathcal{V}$ expressions

No Comments

No Known Activations