INDEX

Explanations

lists and structured points

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

listing points and items

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

msgTypes

-0.60

ScopeManager

-0.49

OGND

-0.49

ISupport

-0.48

 Inoue

-0.40

 مشين

-0.40

modelBuilder

-0.40

olkien

-0.40

 Verhältnisse

-0.40

canestro

-0.40

POSITIVE LOGITS

AccessorTable

0.52

 Audiodateien

0.49

 factors

0.49

 Factors

0.45

 fatores

0.45

ThroughAttribute

0.45

Factors

0.44

featureID

0.43

 checklist

0.43

 fattori

0.42

Activations Density 0.380%

lists and structured points

listing points and items

No Comments

No Known Activations