INDEX

Explanations

references to healthcare and health-related studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

OGND

-0.86

ConstraintMaker

-0.84

parsedMessage

-0.81

tvguidetime

-0.78

出版年

-0.78

esModule

-0.75

StoryboardSegue

-0.74

 uVar

-0.69

>{@

-0.68

PyExc

-0.68

POSITIVE LOGITS

 para

0.49

dorf

0.48

ration

0.45

vocable

0.45

']):

0.45

uell

0.44

롯

0.44

'>"

0.43

 בית

0.43

 trama

0.42

Activations Density 0.036%

references to healthcare and health-related studies

No Comments

No Known Activations