INDEX

Explanations

numerical data, particularly in tabular formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

and

-0.58

-0.54

or

-0.47

ist

-0.46

 oike

-0.44

owna

-0.42

 вся

-0.41

and

-0.41

soka

-0.40

http

-0.38

POSITIVE LOGITS

Datuak

1.08

expandindo

0.95

verwijspagina

0.86

 estekak

0.86

WebVitals

0.84

 linkovi

0.84

Hentet

0.79

Przypisy

0.79

 snippetHide

0.77

 ExecuteAsync

0.77

Activations Density 0.098%

numerical data, particularly in tabular formats

No Comments

No Known Activations