INDEX

Explanations

syntax elements and informational structure in programming documentation

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

Code comments or documentation

np_acts-logits-general · gemini-2.0-flash

documentation comments and code

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

<eos>

-0.73

 toch

-0.49

Now

-0.48

 तो

-0.48

++;

-0.47

↵↵

-0.47

now

-0.46

вле

-0.46

 indeed

-0.46

now

-0.46

POSITIVE LOGITS

 Infórmanos

0.82

 للاسماء

0.78

haviour

0.75

^(@)

0.72

featureID

0.72

GOTREF

0.70

RectangleBorder

0.67

olesale

0.67

 &___

0.67

CppCodeGen

0.66

Activations Density 0.373%

syntax elements and informational structure in programming documentation

Code comments or documentation

documentation comments and code

No Comments

No Known Activations