INDEX

Explanations

tokens related to programming syntax and structure

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

Preceding math symbols or foreign characters

np_acts-logits-general · gemini-2.0-flash

Case definition

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

<h4>

-0.60

-0.59

</td>

-0.59

(){

-0.58

-0.57

-0.55

<td>

-0.55

-0.54

POSITIVE LOGITS

 مشين

1.03

Efq

1.01

脚注の使い方

0.87

 itſelf

0.86

 تانيه

0.85

 MainAxisSize

0.85

 snippetHide

0.84

 الرياضيه

0.81

قایناقلار

0.81

RenderAtEndOf

0.81

Activations Density 0.367%

tokens related to programming syntax and structure

Preceding math symbols or foreign characters

Case definition

No Comments

No Known Activations