INDEX

Explanations

references to technical fields or categories in formal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

McN

-0.51

onus

-0.50

 Bonner

-0.50

 Svensson

-0.49

onto

-0.48

 Swanson

-0.48

onSave

-0.47

 Caron

-0.47

addto

-0.47

Почему

-0.46

POSITIVE LOGITS

 field

2.17

 Field

2.02

Field

1.98

 FIELD

1.88

field

1.88

 fields

1.80

 Fields

1.73

FIELD

1.68

Fields

1.66

fields

1.65

Activations Density 0.139%

references to technical fields or categories in formal documentation

No Comments

No Known Activations