INDEX

Explanations

indications of specific programming structures or code manipulation activities

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

javascript or code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

ChildScrollView

-0.81

GraphicsUnit

-0.75

aarrggbb

-0.74



-0.72

InputBorder

-0.71

bootstrapcdn

-0.69

HasForeignKey

-0.69

PerformLayout

-0.68

 hObject

-0.66

LLocation

-0.66

POSITIVE LOGITS

Koordinaten

0.35

0.33

 Independencia

0.32

 McGuire

0.32

theo

0.31

Projekt

0.30

 tramo

0.30

</table>

0.30

section

0.29

squareup

0.29

Activations Density 0.058%

indications of specific programming structures or code manipulation activities

javascript or code snippets

No Comments

No Known Activations