INDEX

Explanations

scientific terminology related to taxonomy, specifically for identifying genera and species within biological classifications

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

genus names

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 المعيارى

-0.77

setVerticalGroup

-0.72

Kjelder

-0.67

 estekak

-0.66

 queſta

-0.66

⟬

-0.65

sizeCache

-0.65

Билгалдахарш

-0.64

 protoimpl

-0.64

writeFieldEnd

-0.63

POSITIVE LOGITS

 geslacht

0.42

 Gattung

0.42

 genus

0.40

ficación

0.34

 establecidos

0.33

 брен

0.33

 réservoir

0.31

 linguri

0.31

Gön

0.31

 domésticos

0.30

Activations Density 0.012%

scientific terminology related to taxonomy, specifically for identifying genera and species within biological classifications

genus names

No Comments

No Known Activations