INDEX

Explanations

references to editorial roles and processes

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

saraba

-0.81

Παραπομπές

-0.77

Билгалдахарш

-0.75

Życiorys

-0.73

IBAction

-0.73

 Réponses

-0.73

WebVitals

-0.71

'',

-0.71

withIdentifier

-0.69

Kah

-0.68

POSITIVE LOGITS

 editor

2.42

 Editor

2.31

 editors

2.30

editor

2.14

 Editors

2.08

Editor

2.04

 EDITOR

1.98

Editors

1.92

 editing

1.87

 Editing

1.79

Activations Density 0.047%

references to editorial roles and processes

No Comments

No Known Activations