INDEX

Explanations

references to laboratory studies and experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 Merr

-1.02

 Lein

-0.78

openhauer

-0.76

ücks

-0.71

franch

-0.70

writerow

-0.69

 étoit

-0.69

 Oblivion

-0.69

 upholstered

-0.68

 Theſe

-0.67

POSITIVE LOGITS

Lab

1.53

lab

1.46

Lab

1.45

 labs

1.39

LAB

1.35

 laboratory

1.30

 laboratories

1.29

LAB

1.29

lab

1.27

 Laboratory

1.24

Activations Density 0.100%

references to laboratory studies and experiments

No Comments

No Known Activations