INDEX

Explanations

changes in names, values, or metrics over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

 AssemblyTitle

-0.45

Loh

-0.43

AnchorTagHelper

-0.42

 zanah

-0.42

CONSIN

-0.41

xel

-0.40

 diff

-0.40

 AssemblyCompany

-0.40

wohl

-0.39

PARATOR

-0.39

POSITIVE LOGITS

to

1.28

到

0.97

至

0.90

 into

0.87

 kepada

0.84

 إلى

0.83

 naar

0.80

 đến

0.79

 vnto

0.78

CloseOperation

0.76

Activations Density 0.400%

changes in names, values, or metrics over time

No Comments

No Known Activations