INDEX

Explanations

content related to research and academic investigation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 发表于

-0.52

printLine

-0.48

 Polsek

-0.48

 GlobalKey

-0.47

 createState

-0.45

addContainerGap

-0.44

crever

-0.43

flashdata

-0.43

ňov

-0.42

vician

-0.42

POSITIVE LOGITS

 research

2.48

 researched

2.28

 researching

2.26

research

2.21

Research

2.09

 Research

2.08

 RESEARCH

1.99

 researches

1.94

 googling

1.92

RESEARCH

1.87

Activations Density 0.488%

content related to research and academic investigation

No Comments

No Known Activations