INDEX

Explanations

technical terms and symbols related to programming and computation

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

-0.65

-0.62

-0.59

in

-0.56

-0.54

-0.53

to

-0.52

POSITIVE LOGITS

Personendaten

1.29

Efq

1.24

 myſelf

1.22

 EconPapers

1.20

 purpoſe

1.19

 Monfieur

1.18

 AssemblyCulture

1.16

 itſelf

1.12

帖最后由

1.12

 houſe

1.10

Activations Density 0.826%

technical terms and symbols related to programming and computation

No Comments

No Known Activations