INDEX

Explanations

references to statistical studies, models, or data analysis methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Shakspeare

-0.86

SequentialGroup

-0.83

 houſe

-0.74

 Shaksp

-0.72

 برانيه

-0.72

 itſelf

-0.70

 preſent

-0.70

 purpoſe

-0.69

ChromeDriver

-0.69

^(@)

-0.68

POSITIVE LOGITS

StoryboardSegue

0.50

 transfieras

0.49

ніципа

0.42

ветить

0.41

É

0.40

 disambiguazione

0.40

 ujednoznacz

0.39

◉

0.39

alva

0.38

 mini

0.38

Activations Density 0.199%

references to statistical studies, models, or data analysis methods

No Comments

No Known Activations