INDEX

Explanations

key concepts related to rules, standards, and classifications

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

descriptive word followed by connector

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

RTLR

-0.45

istoitu

-0.42

󠁣

-0.42

tonode

-0.40

plusplus

-0.40

fromLTRB

-0.39

Tembelea

-0.38

DANGER

-0.38

 DEPOS

-0.38

ciless

-0.38

POSITIVE LOGITS

AndEndTag

0.50

 चीज़ों

0.47

contentLoaded

0.46

 ImGui

0.44

FunctionFlags

0.44

новништво

0.44

AnimationsModule

0.42

onViewCreated

0.42

évaluateur

0.40

Marshaller

0.40

Activations Density 0.324%

key concepts related to rules, standards, and classifications

descriptive word followed by connector

No Comments

No Known Activations