INDEX

Explanations

references to specific quantitative or statistical details in a text

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

 виправивши

-0.84

 autorytatywna

-0.75

Datuak

-0.74

Tikang

-0.74

mrc

-0.71

prepareStatement

-0.67

 GIPHY

-0.66

orianCalendar

-0.66

ItemBackground

-0.65

 financières

-0.65

POSITIVE LOGITS

0.83

and

0.80

 plus

0.78

the

0.74

 sowie

0.73

 samt

0.72

以及

0.71

etc

0.70

 oraz

0.70

 וכן

0.69

Activations Density 0.387%

references to specific quantitative or statistical details in a text

No Comments

No Known Activations