INDEX

Explanations

terms related to testing and statistical analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Bous

-0.66

 Lindgren

-0.60

 Bremen

-0.52

 commerciali

-0.51

 inond

-0.49

 mData

-0.49

 fills

-0.49

jenost

-0.49

 Vasili

-0.48

 stof

-0.48

POSITIVE LOGITS

Piz

0.68

styleType

0.66

 pizzeria

0.66

pizz

0.66

INSEE

0.65

 estekak

0.64

 incision

0.64

Baked

0.64

Piz

0.61

piz

0.61

Activations Density 3.195%

terms related to testing and statistical analysis

No Comments

No Known Activations