INDEX

Explanations

references to specific assays related to tropism testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 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

참고

-0.45

 otomatig

-0.41

ymce

-0.41

addPreferredGap

-0.41

sedown

-0.40

$_['

-0.38

liferay

-0.37

::_('

-0.37

 doInBackground

-0.36

 Pernambuco

-0.36

POSITIVE LOGITS

Tro

0.91

Tro

0.86

tro

0.79

tro

0.76

TRO

0.75

TRO

0.68

trophy

0.68

 Trophy

0.66

 Trop

0.65

otro

0.64

Activations Density 0.401%

references to specific assays related to tropism testing

No Comments

No Known Activations