INDEX

Explanations

references to historical scientific contributions and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Diweddarwch

-0.60

DoubleQuotes

-0.54

 förr

-0.51

inander

-0.43

Kenmerken

-0.43

komna

-0.41

 Terima

-0.41

Egypte

-0.41

insics

-0.41

enterOuterAlt

-0.40

POSITIVE LOGITS

outline

0.40

 Eureka

0.39

orino

0.38

 intercepts

0.38

PhysRevD

0.38

chats

0.37

Eureka

0.36

 chats

0.36

 esterni

0.35

 formul

0.35

Activations Density 0.048%

references to historical scientific contributions and events

No Comments

No Known Activations