INDEX

Explanations

mentions of encoding formats, particularly UTF-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AddHtmlAttribute

-0.77

tonode

-0.63

apimachinery

-0.62

 doInBackground

-0.60

Referències

-0.57

tonsoft

-0.57

StackNavigator

-0.56

DotNetBar

-0.56

sidemargin

-0.56

AsUp

-0.56

POSITIVE LOGITS

CodeAttribute

0.64

 Acht

0.54

]<<

0.51

Late

0.50

COND

0.50

 congen

0.49

utf

0.49

GraphicsUnit

0.48

 fusi

0.48

theil

0.47

Activations Density 0.059%

mentions of encoding formats, particularly UTF-related terms

No Comments

No Known Activations