INDEX

Explanations

technical terms related to programming and configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 étoient

-0.93

 auroit

-0.91

 étoit

-0.87

 feroit

-0.86

 avoient

-0.83

setVerticalGroup

-0.83

 ainfi

-0.81

 gärna

-0.80

Enllaces

-0.79

 bezeichneter

-0.78

POSITIVE LOGITS

0.60

 other

0.60

des

0.60

less

0.58

 back

0.57

0.56

 control

0.54

per

0.52

back

0.52

 again

0.51

Activations Density 2.185%

technical terms related to programming and configuration

No Comments

No Known Activations