INDEX

Explanations

specific names and technical terms related to production and design in various fields

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

Lebesgue measure

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

 død

-0.43

 Schluß

-0.43

 règne

-0.43

tagHelperRunner

-0.43

deutig

-0.42

 Defensa

-0.42

 nød

-0.42

 inimigo

-0.42

 ब्रेकडाउन

-0.41

textAlignment

-0.41

POSITIVE LOGITS

 Labrador

0.90

 Hokkaido

0.82

esgue

0.82

 Radisson

0.76

北海道

0.73

 labrador

0.72

 Eskimo

0.72

Esk

0.71

FieldDescriptor

0.68

 Haskell

0.68

Activations Density 0.006%

specific names and technical terms related to production and design in various fields

Lebesgue measure

No Comments

No Known Activations