INDEX

Explanations

tags and XML-like markup structures in the text

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

Code snippets and programming-related terms

np_acts-logits-general · gemini-2.0-flash

spans less than

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

 getById

-0.38

 Ausdruck

-0.35

 nélkül

-0.35

 Lösungen

-0.32

 venganza

-0.32

 Schülern

-0.31

的東西

-0.30

 cifra

-0.30

 Farbe

-0.30

 Eindruck

-0.30

POSITIVE LOGITS

exitRule

0.75

jspb

0.71

 للمعارف

0.66

 actual

0.66

 Curr

0.63

 Actual

0.63

 jspb

0.60

transQ

0.60

AccessorTable

0.59

SharedCtor

0.59

Activations Density 0.500%

tags and XML-like markup structures in the text

Code snippets and programming-related terms

spans less than

No Comments

No Known Activations