INDEX

Explanations

coding constructs and structure, particularly related to programming functions and their syntax

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

Code-related symbols

np_acts-logits-general · gemini-2.0-flash

code snippets and definitions

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

Datuak

-0.82

igno

-0.67

utet

-0.64

Zel

-0.61

Kel

-0.61

DEZ

-0.61

 Dolan

-0.60

 Puli

-0.59

 comuniques

-0.59

لاعب

-0.59

POSITIVE LOGITS

\{\\

0.71

 puissent

0.69

fél

0.65

ruptedException

0.63

<tfoot>

0.63

bbene

0.63

 remercier

0.63

 tarko

0.63

antaranya

0.63

 Slavic

0.63

Activations Density 0.064%

coding constructs and structure, particularly related to programming functions and their syntax

Code-related symbols

code snippets and definitions

No Comments

No Known Activations