INDEX

Explanations

terms related to legal or procedural denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Busch

-0.69

 Holloway

-0.68

 MonoBehaviour

-0.66

PropertyChanging

-0.66

 viewDidLoad

-0.63

Vla

-0.61

 Boch

-0.61

 Maguire

-0.61

Busch

-0.61

POSITIVE LOGITS

 ་་

1.09

MCP

1.03

 doubtnut

0.99

PDS

0.96

 Arxivat

0.96

 Trix

0.94

IRC

0.93

NFS

0.93

 Darlene

0.92

NFS

0.92

Activations Density 0.724%

terms related to legal or procedural denial

No Comments

No Known Activations