INDEX

Explanations

terms related to hierarchical classifications and categories

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

Hierarchical classifications and ontologies

np_acts-logits-general · gemini-2.0-flash

classification codes and ontology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ChildScrollView

-0.66

 يتيمه

-0.63

 ſeine

-0.62

 '\\;'

-0.60

 snippetHide

-0.60

 CreateTagHelper

-0.57

gdx

-0.57

+#+#

-0.56

rungsseite

-0.55

GTCX

-0.55

POSITIVE LOGITS

 classification

0.51

 categories

0.43

 Classification

0.42

 hierarchy

0.42

 taxonomy

0.41

分类

0.40

 category

0.40

 classifications

0.40

Tree

0.39

 Tree

0.39

Activations Density 0.568%

terms related to hierarchical classifications and categories

Hierarchical classifications and ontologies

classification codes and ontology

No Comments

No Known Activations