INDEX

Explanations

programming-related conditional statements and logical checks

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

Code snippets and mathematical expressions

np_acts-logits-general · gemini-2.0-flash

0-indexed positions

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

PreferredItem

-0.88

queryInterface

-0.71

aarrggbb

-0.69

 indisponible

-0.67

ProgressHUD

-0.61

estima

-0.60

pushFollow

-0.60

脚注の使い方

-0.58

/\.

-0.57

Искәрмәләр

-0.56

POSITIVE LOGITS

Huf

0.56

abag

0.52

 proef

0.49

הערות

0.49

ControllerAdvice

0.48

 carreaux

0.46

Nol

0.45

miral

0.45

Diagonal

0.45

gridx

0.45

Activations Density 0.093%

programming-related conditional statements and logical checks

Code snippets and mathematical expressions

0-indexed positions

No Comments

No Known Activations