INDEX

Explanations

programming-related syntax and keywords

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

Code, especially annotations and function declarations

np_acts-logits-general · gemini-2.0-flash

code comments and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

<eos>

-0.65

 otomatig

-0.57

MockMvc

-0.56

 Media

-0.47

-0.46

 CanadaChoose

-0.46

webElementXpaths

-0.46

<?

-0.45

↵↵

-0.45

 Much

-0.45

POSITIVE LOGITS

noinspection

0.80

seamnă

0.71

 Ferner

0.65

berdayakan

0.64

 تضيفلها

0.63

 AssemblyTitle

0.62

ORETICAL

0.62

 devriez

0.61

 ainfi

0.61

lgari

0.61

Activations Density 0.088%

programming-related syntax and keywords

Code, especially annotations and function declarations

code comments and structure

No Comments

No Known Activations