INDEX

Explanations

terms and concepts related to host-pathogen interactions and epidemiological models

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

Scientific or mathematical notation

np_acts-logits-general · gemini-2.0-flash

biological or statistical measurements

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

richTextPanel

-0.52

ufficio

-0.50

 sellado

-0.49

 مشين

-0.49

AccessorTable

-0.46

AddTagHelper

-0.45

IUrlHelper

-0.45

存于互联网档案馆

-0.45

 محفوظة

-0.43

 proyección

-0.43

POSITIVE LOGITS

="{{

0.47

 Stochastic

0.41

{{$

0.39

 resources

0.38

>{{

0.38

ResourceId

0.37

 strán

0.37

utian

0.37

 stochastic

0.37

 constraints

0.36

Activations Density 1.502%

terms and concepts related to host-pathogen interactions and epidemiological models

Scientific or mathematical notation

biological or statistical measurements

No Comments

No Known Activations