INDEX

Explanations

references to measurement ranges or scopes in data

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Mooney

-0.90

 blessé

-0.85

 Hül

-0.85

 Witkin

-0.80

 Nutt

-0.79

 bookId

-0.79

 Mistakes

-0.78

 médicaux

-0.77

letus

-0.76

 Kowalski

-0.73

POSITIVE LOGITS

 ranges

1.75

 range

1.69

 Range

1.62

 RANGE

1.56

range

1.49

ranges

1.48

Range

1.45

 Ranges

1.44

RANGE

1.41

Ranges

1.41

Activations Density 0.070%

references to measurement ranges or scopes in data

No Comments

No Known Activations