INDEX

Explanations

terms related to immune system function and health

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

immune system function

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

tla

-0.49

 Reverso

-0.47

 հղումներ

-0.47

slidesPer

-0.46

Obrázky

-0.45

Filmografie

-0.44

addPreferredGap

-0.44

inição

-0.43

UserDto

-0.42

ViewInit

-0.42

POSITIVE LOGITS

 immune

0.74

 immun

0.64

 Immune

0.63

immune

0.61

 immunity

0.60

 inmun

0.60

immun

0.58

Immune

0.57

 imun

0.57

免疫

0.56

Activations Density 0.040%

terms related to immune system function and health

immune system function

No Comments

No Known Activations