INDEX

Explanations

programming constructs and syntax elements

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

Code snippets with loops

np_acts-logits-general · gemini-2.0-flash

loop termination

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 الدولى

-0.63

enseits

-0.52

 Phần

-0.50

 hammer

-0.50

 unmodified

-0.49

 quotas

-0.48

ⓘ

-0.48

 Sodom

-0.48

 xrange

-0.48

rotnie

-0.47

POSITIVE LOGITS

++){

0.65

windowFixed

0.64

'])){

0.64

 autorytatywna

0.61

reactstrap

0.61

Personendaten

0.60

CppCodeGen

0.60

 endwhile

0.60

 CascadeType

0.58

endwhile

0.57

Activations Density 0.046%

programming constructs and syntax elements

Code snippets with loops

loop termination

No Comments

No Known Activations