INDEX

Explanations

programming-related terms and constructs

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

iterator constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

fillType

-0.73

ſelf

-0.73

ագրություններ

-0.72

 queſta

-0.72

 ſei

-0.70

ſelves

-0.69

 auroit

-0.68

 viewDidLoad

-0.66

 feroit

-0.66

⮕

-0.66

POSITIVE LOGITS

iterator

0.42

 consultato

0.35

Iterator

0.33

Anhalt

0.30

 Ávila

0.30

 Otero

0.30

 testigos

0.29

 iterator

0.27

complexType

0.27

 search

0.26

Activations Density 0.017%

programming-related terms and constructs

iterator constructs

No Comments

No Known Activations