INDEX

Explanations

specific terms related to technical properties and features in various contexts

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

Code, file paths, or programming-related text

np_acts-logits-general · gemini-2.0-flash

specific token followed by common continuations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

detectChanges

-0.62

Carriera

-0.50

Palmarès

-0.47

 OMITTED

-0.47

 surla

-0.47

 Disqus

-0.47

ulz

-0.46

 nahilalakip

-0.45

 kaarangay

-0.45

})^{

-0.44

POSITIVE LOGITS

IContainer

0.76

 HasFactory

0.69

Personensuche

0.64

 BrowserModule

0.63

writeField

0.62

RenderAtEndOf

0.62

WebElementEntity

0.61

BrowserModule

0.60

InvalidProtocol

0.58

########.

0.58

Activations Density 2.598%

specific terms related to technical properties and features in various contexts

Code, file paths, or programming-related text

specific token followed by common continuations

No Comments

No Known Activations