INDEX

Explanations

tokens or keywords related to API operations and error handling in code

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

coding-related language constructs and operations

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

Objective-C method signatures

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

śred

-0.51

reg

-0.51

Enllaces

-0.49

init

-0.47

 réputation

-0.46

衷

-0.45

 mukana

-0.44

Results

-0.43

 initWithFrame

-0.43

 picioare

-0.43

POSITIVE LOGITS

Datuak

0.67

évaluateur

0.65

 Мексичка

0.64

❮

0.58

 تكبرها

0.57

 phenomen

0.56

queryInterface

0.55

(!__

0.55

دانشنامهٔ

0.55

himo

0.55

Activations Density 0.178%

tokens or keywords related to API operations and error handling in code

coding-related language constructs and operations

Objective-C method signatures

No Comments

No Known Activations