INDEX

Explanations

structured code elements and assertions in programming

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

Code-related terms or names

np_acts-logits-general · gemini-2.0-flash

API calls and technical terms

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

↵↵↵

-0.99

AnchorStyles

-0.74

 Majefty

-0.67

errHandler

-0.63

ificantly

-0.60

 Monfieur

-0.60

 perſ

-0.60

enumi

-0.58

 parentheses

-0.58

}\\

-0.57

POSITIVE LOGITS

 propOrder

0.66

PhysRev

0.55

copyOf

0.53

Personendaten

0.52

mtliche

0.48

الدراسه

0.47

matchCondition

0.46

 ThemeData

0.44

consulté

0.42

GATE

0.40

Activations Density 0.068%

structured code elements and assertions in programming

Code-related terms or names

API calls and technical terms

No Comments

No Known Activations