INDEX

Explanations

technical and legal terms related to business and health contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

DoubleQuotes

-0.70

MLLoader

-0.61

 المعيارى

-0.61

 saites

-0.58

openqa

-0.57

AndEndTag

-0.57

labelledby

-0.57

إنه

-0.56

ViewImports

-0.54

glTranslatef

-0.53

POSITIVE LOGITS

 AssemblyCulture

0.64

#+#

0.52

Dox

0.51

 SafeMath

0.50

 Judah

0.50

ImageContext

0.49

<bos>

0.49

 Wikiseite

0.48

 "'");

0.48

 invokingState

0.48

Activations Density 1.114%

technical and legal terms related to business and health contexts

No Comments

No Known Activations