INDEX

Explanations

keywords and structure related to programming classes and methods, particularly in Java

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 abbey

-0.66

 abbot

-0.63

المشاركات

-0.60

 Tric

-0.58

 gondola

-0.58

 scab

-0.57

 bosom

-0.57

Lyt

-0.57

Mâ

-0.57

 loudest

-0.57

POSITIVE LOGITS

IBOutlet

0.97

IBAction

0.70

 autorytatywna

0.69

InjectAttribute

0.65

 consultato

0.62

 supérieures

0.62

 supérieurs

0.61

 ModelExpression

0.61

Välislingid

0.57

 fermée

0.56

Activations Density 0.086%

keywords and structure related to programming classes and methods, particularly in Java

No Comments

No Known Activations