INDEX

Explanations

sections of code related to "TODO" comments or autogenerated methods in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

transQ

-0.65

 سكانية

-0.54

 Dasar

-0.54

 تانيه

-0.53

 mignon

-0.51

InjectAttribute

-0.50

 Ministre

-0.49

 rappresent

-0.49

 Arhivirano

-0.48

 незавершена

-0.47

POSITIVE LOGITS

 lenker

0.67

 AssemblyCulture

0.63

WebVitals

0.63

 مشين

0.62

TypedDataSet

0.62

posób

0.61

StoryboardSegue

0.61

hyrchwyd

0.61

 estimés

0.60

ValueGenerated

0.59

Activations Density 0.025%

sections of code related to "TODO" comments or autogenerated methods in programming

No Comments

No Known Activations