INDEX

Explanations

references to scientific terms and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Schließlich

-0.37

 Vögel

-0.36

oggi

-0.35

 Ecke

-0.34

-0.33

 Kriege

-0.33

 Sünde

-0.33

 Opfer

-0.32

 Einer

-0.32

 Vereinigung

-0.32

POSITIVE LOGITS

AddTagHelper

0.96

 AssemblyCulture

0.80

 فريبيس

0.79

 ब्रेकडाउन

0.77

hyrchwyd

0.74

iſten

0.72

MessageOf

0.72

rungsseite

0.71

 otomatig

0.71

 MainAxisSize

0.70

Activations Density 0.908%

references to scientific terms and concepts

No Comments

No Known Activations