INDEX

Explanations

references to Northern regions and locations

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

 Schultz

-0.99

 Schulz

-0.83

 Marquez

-0.82

 Gonzalez

-0.81

</table>

-0.81

Hak

-0.77

č

-0.77

ｕ

-0.76

vač

-0.75

 Schumacher

-0.72

POSITIVE LOGITS

SEVERE

1.04

ValueStyle

1.01

 Heere

0.95

 EnglishChoose

0.95

/*---

0.91

CWE

0.88

 Arcane

0.86

CloseOperation

0.85

 pylint

0.83

 fevere

0.82

Activations Density 0.214%

references to Northern regions and locations

No Comments

No Known Activations