INDEX

Explanations

references to drawing or graphical elements in programming contexts

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

Code snippets with file paths or URLs

np_acts-logits-general · gemini-2.0-flash

drawing and localhost

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

SourceChecksum

-0.85

addCriterion

-0.72

:✨

-0.72

 unknownFields

-0.70

HasForeignKey

-0.70

AndroidJUnit

-0.67

windowFixed

-0.66

InjectAttribute

-0.63

|}{$

-0.63

PhysRevD

-0.63

POSITIVE LOGITS

Drawing

1.12

 Drawing

0.94

 ―――――

0.76

 drawing

0.75

 iſt

0.71

drawing

0.70

Efq

0.69

 drawings

0.68

 DRAWING

0.68

ſelf

0.63

Activations Density 0.003%

references to drawing or graphical elements in programming contexts

Code snippets with file paths or URLs

drawing and localhost

No Comments

No Known Activations