INDEX

Explanations

terms related to classification and categorization of proteins, especially focusing on unclassified or ambiguously classified proteins

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

classification and unexplained status

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

VersionUID

-0.48

⅘

-0.45

OleDb

-0.42

-------------</

-0.41

contentLoaded

-0.41

Gruss

-0.41

ysław

-0.41

龇

-0.40

TypedDataSet

-0.39

 ChromeDriver

-0.39

POSITIVE LOGITS

httphttps

0.47

 pertence

0.46

 Unclassified

0.46

 unexplained

0.45

 clasificación

0.43

 clasific

0.42

 EconPapers

0.42

classified

0.41

lassification

0.40

 undivided

0.40

Activations Density 0.219%

terms related to classification and categorization of proteins, especially focusing on unclassified or ambiguously classified proteins

classification and unexplained status

No Comments

No Known Activations