INDEX

Explanations

references to different segments or components in a structured context, such as software or data organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ed

-0.80

</table>

-0.74

 Lawler

-0.73

 nicio

-0.73

eyes

-0.73

acağına

-0.71

รับ

-0.69

 byen

-0.69

 Cathy

-0.68

away

-0.68

POSITIVE LOGITS

 sement

1.03

ant

1.02

ANT

0.98

uent

0.94

nent

0.93

ulant

0.90

EMENT

0.88

ulants

0.85

nant

0.85

 nant

0.84

Activations Density 0.317%

references to different segments or components in a structured context, such as software or data organization

No Comments

No Known Activations