INDEX

Explanations

mathematical symbols and notation related to matrix transformations and operations

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

principalColumn

-0.65

tagHelperRunner

-0.54

 AspNetCore

-0.52

twimg

-0.50

anum

-0.45

Efq

-0.45

 BorderSide

-0.43

endaft

-0.42

Datuak

-0.41

ană

-0.41

POSITIVE LOGITS

 sequentially

0.43

 consecutive

0.43

 cumulative

0.43

cumulative

0.43

Cumulative

0.43

 successive

0.42

 successively

0.42

 layers

0.41

 sequential

0.41

 layered

0.41

Activations Density 1.205%

mathematical symbols and notation related to matrix transformations and operations

No Comments

No Known Activations