INDEX

Explanations

syntax-related patterns and structure in programming or markup languages

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

html comments and code directives

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

SuspendLayout

-0.30

Erreferentziak

-0.30

 navegando

-0.28

henswürdigkeiten

-0.26

never

-0.26

another

-0.26

 vorm

-0.25

Muy

-0.25

 Mün

-0.24

طر

-0.24

POSITIVE LOGITS

IsMutable

0.74

хьтан

0.68

ConstraintMaker

0.63

 ویکی‌پدی

0.59

Tembelea

0.58

sizeCache

0.57

processable

0.56

 صوتيه

0.56

 كورة

0.55

licone

0.55

Activations Density 0.128%

syntax-related patterns and structure in programming or markup languages

html comments and code directives

No Comments

No Known Activations