INDEX

Explanations

technical terms and references related to programming and software development

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

 fubject

-0.63

 ordf

-0.60

 calum

-0.58

 fuper

-0.57

 pleaſure

-0.55

 quæ

-0.55

 contextLoads

-0.54

 Irregular

-0.52

 purpoſe

-0.52

 stället

-0.52

POSITIVE LOGITS

REASONS

0.71

 REASONS

0.71

sens

0.71

 included

0.71

/*

0.71

RenderAtEndOf

0.67

帖最后由

0.66

 raisons

0.66

CppMethod

0.65

uxxxx

0.64

Activations Density 2.928%

technical terms and references related to programming and software development

No Comments

No Known Activations