INDEX

Explanations

references to Java programming language versions and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 track

-0.51

THON

-0.50

 diri

-0.46

 tracks

-0.46

OVERY

-0.46

škin

-0.44

cá

-0.44

track

-0.44

 structure

-0.43

 independently

-0.43

POSITIVE LOGITS

 PLANNING

0.92

 JAVA

0.90

 Planning

0.90

Planning

0.90

 planning

0.89

java

0.87

planning

0.85

enumi

0.85

rawDesc

0.84

 Planner

0.83

Activations Density 0.160%

references to Java programming language versions and related terms

No Comments

No Known Activations