INDEX

Explanations

technical terms and descriptions related to shapes and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

tonsoft

-0.42

postsleuth

-0.40

 deleg

-0.36

 intram

-0.34

LikeLiked

-0.34

 Lightboxes

-0.34

UserScript

-0.33

 Decke

-0.33

 tantum

-0.32

 дуб

-0.32

POSITIVE LOGITS

 shape

1.07

 shaped

0.96

 shapes

0.93

shaped

0.91

 Shape

0.85

shape

0.80

Shape

0.78

 Shaped

0.78

Shaped

0.76

 kształ

0.74

Activations Density 0.999%

technical terms and descriptions related to shapes and structures

No Comments

No Known Activations