INDEX

Explanations

elements related to programming and input formatting functions

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

Programming terms and names

np_acts-logits-general · gemini-2.0-flash

coding structures and text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

{};

-0.58

="@+

-0.58

<>();

-0.57

@"/

-0.57

CodeDom

-0.57

󠁿

-0.55

//{

-0.53

omitempty

-0.52

_;

-0.51

POSITIVE LOGITS

 InputDecoration

0.84

 GoogleFonts

0.64

 ThemeData

0.60

bootstrapcdn

0.60

 للاسماء

0.59

 politiet

0.56

 الرياضيه

0.56

 SwiftUI

0.56

 BoxDecoration

0.55

 SizedBox

0.54

Activations Density 0.015%

elements related to programming and input formatting functions

Programming terms and names

coding structures and text

No Comments

No Known Activations