INDEX

Explanations

technical claims and descriptions related to semiconductor devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

out

-0.48

once

-0.47

<code>

-0.46

bef

-0.46

beta

-0.45

zul

-0.45

alpha

-0.44

дке

-0.44

rov

-0.43

caj

-0.43

POSITIVE LOGITS

 kasarigan

1.09

GEBURTSDATUM

1.08

rungsseite

0.90

 kaarangay

0.76

nemia

0.75

!*\

0.74

PMailer

0.73

 }}$}

0.73

saurus

0.73

abestanden

0.71

Activations Density 0.181%

technical claims and descriptions related to semiconductor devices

No Comments

No Known Activations