INDEX

Explanations

terms related to recurrent processes or concepts

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

 GenerationType

-0.55

localctx

-0.49

ApiProperty

-0.38

ArgumentParser

-0.37

 Exactos

-0.35

 appetites

-0.33

 invitamos

-0.32

 nhat

-0.32

########.

-0.32

miyorum

-0.32

POSITIVE LOGITS

 PagesJaunes

0.60

 وتسجيلات

0.55

Viitteet

0.51

 Réponses

0.50

SequentialGroup

0.50

Previous

0.49

Diweddarwch

0.47

↹

0.45

 precedenti

0.45

\{\\

0.45

Activations Density 1.486%

terms related to recurrent processes or concepts

No Comments

No Known Activations