INDEX

Explanations

keywords and classifications in structured data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

новништво

-0.66

imageshack

-0.60

rungsseite

-0.59

SpringBootTest

-0.59

CompleteListener

-0.59

richTextPanel

-0.58

AnimationsModule

-0.58

횟

-0.57



-0.57

 surla

-0.54

POSITIVE LOGITS

 tags

0.52

 keywords

0.41

 classification

0.39

 classifications

0.39

 Classification

0.38

tags

0.37

 Tags

0.36

 genre

0.35

 categorization

0.34

 CLASSIFICATION

0.34

Activations Density 0.482%

keywords and classifications in structured data

No Comments

No Known Activations