INDEX

Explanations

references to "series" and related terms

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

near "series" and "serial"

np_acts-logits-general · gemini-2.0-flash

series regression estimators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

 estekak

-0.64

 BoxFit

-0.62

Panamoan

-0.58

 tiguan

-0.55

 Савезне

-0.52

 Walkover

-0.51

ANTLR

-0.51

 informée

-0.50

yntaxException

-0.50

ïlande

-0.50

POSITIVE LOGITS

 Serial

0.65

 serial

0.65

Serial

0.61

 Series

0.57

 SERIAL

0.56

serial

0.55

 series

0.52

Series

0.51

SER

0.51

 SERIES

0.50

Activations Density 0.132%

references to "series" and related terms

near "series" and "serial"

series regression estimators

No Comments

No Known Activations