INDEX

Explanations

references to specific types of trees or tree-related terms

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

Types of trees

np_acts-logits-general · gemini-2.0-flash

tree names and places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

+#+#

-1.04

ReusableCell

-0.84

tonsoft

-0.79

tagext

-0.77

AsUp

-0.73

aarrggbb

-0.72

IntoConstraints

-0.72

makeConstraints

-0.70

Personensuche

-0.70

 Réponses

-0.70

POSITIVE LOGITS

 tree

0.73

 Tree

0.72

 trees

0.69

leaf

0.69

 TREE

0.67

 Grove

0.65

 leaf

0.65

tree

0.64

wood

0.62

Tree

0.61

Activations Density 0.260%

references to specific types of trees or tree-related terms

Types of trees

tree names and places

No Comments

No Known Activations