INDEX

Explanations

references to resources in various contexts

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

preceding "resource"

np_acts-logits-general · gemini-2.0-flash

resource managers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

WebServlet

-0.81

BufferException

-0.65

("")]

-0.63

Démographie

-0.56

PointerException

-0.56

posedge

-0.55

IndentedString

-0.55

 GenerationType

-0.55

قایناقلار

-0.54

__":

-0.53

POSITIVE LOGITS

fulness

1.03

ful

0.61

fully

0.59

 allocation

0.59

 Allocation

0.55

allocation

0.52

FUL

0.50

AsStream

0.49

 humaines

0.49

 umane

0.49

Activations Density 0.068%

references to resources in various contexts

preceding "resource"

resource managers

No Comments

No Known Activations