INDEX

Explanations

programming-related terms and structures

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

Code-related tokens and namespaces

np_acts-logits-general · gemini-2.0-flash

`using System` and namespaces

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

/\.

-0.60

 MotionEvent

-0.60

phinx

-0.58

 moat

-0.58

 LCCN

-0.58

modelBuilder

-0.57

 Pizarro

-0.57

PullParser

-0.55

WriteAttribute

-0.55

 détru

-0.54

POSITIVE LOGITS

 System

0.94

System

0.89

 sistem

0.63

awtextra

0.55

 تضيفلها

0.55

 SYSTEM

0.54

system

0.53

 Sistem

0.53

 Metro

0.52

Bun

0.51

Activations Density 0.020%

programming-related terms and structures

Code-related tokens and namespaces

`using System` and namespaces

No Comments

No Known Activations