INDEX

Explanations

references to technical or programming-related terms and identifiers

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

 betweenstory

-0.71

 مرئيه

-0.56

IContainer

-0.54

WriteTagHelper

-0.50

########.

-0.50

 AppCompatTheme

-0.49

UnusedPrivate

-0.47

ſſung

-0.47

ésultats

-0.47

 ModelExpression

-0.47

POSITIVE LOGITS

GEBURTS

0.47

 disambiguazione

0.41

VersionUID

0.40

homonymie

0.40

 ujednoznacz

0.39

 Stille

0.35

TacToe

0.35

 Davis

0.35

 saka

0.34

 nyelven

0.33

Activations Density 0.125%

references to technical or programming-related terms and identifiers

No Comments

No Known Activations