INDEX

Explanations

technical terms and code-related phrases likely pertaining to file paths or module structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 darse

-0.36

 líquida

-0.35

 بند

-0.35

 totalt

-0.35

 Grüsse

-0.34

 Técnica

-0.34

 Schrauben

-0.34

clamp

-0.33

 nakalista

-0.33

setImageBitmap

-0.33

POSITIVE LOGITS

LookAnd

0.67

FXMLLoader

0.65

rawDesc

0.62

 ErrIntOverflow

0.60

FromNib

0.60

 "..\..\..\

0.54

UrlResolution

0.54

ComponentScan

0.54

/\.

0.54

styleUrls

0.54

Activations Density 0.600%

technical terms and code-related phrases likely pertaining to file paths or module structures

No Comments

No Known Activations