INDEX

Explanations

connections and relationships between concepts or items

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

Follows a noun

np_acts-logits-general · gemini-2.0-flash

linking related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

nikahan

-0.43

 orejas

-0.42

 Arque

-0.40

 Krü

-0.40

 kautta

-0.39

masalahan

-0.39

 fragen

-0.38

趋

-0.38

worpen

-0.38

Litteratur

-0.38

POSITIVE LOGITS

RenderAtEndOf

0.77



0.60

脚注の使い方

0.58

 cherchés

0.50

 kasarigan

0.49

 EconPapers

0.47

ftagPool

0.46

InitVars

0.46

XmlAccessType

0.46

protoimpl

0.45

Activations Density 0.753%

connections and relationships between concepts or items

Follows a noun

linking related concepts

No Comments

No Known Activations