INDEX

Explanations

programming or coding terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ConstraintMaker

-0.69

Hentet

-0.65

下载附件

-0.65

AccessorTable

-0.59

исленность

-0.55

原始内容存档于

-0.53

 defaultstate

-0.52

UserScript

-0.50

varargin

-0.50

UrlResolution

-0.49

POSITIVE LOGITS

EndContext

0.67

 متعلقه

0.63

مصادر

0.61

featureID

0.61

 թվական

0.59

kaido

0.56

脚注の使い方

0.56

<_>

0.54

ronpa

0.54

허

0.53

Activations Density 0.563%

programming or coding terms and structures

No Comments

No Known Activations