INDEX

Explanations

references to specific individuals, organizations, or concepts associated with legal or technical topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

 vettoriale

-0.46

 protoimpl

-0.44

󠁢

-0.43

mployment

-0.42

parsedMessage

-0.41

 tand

-0.41

 Halen

-0.40

MigrationBuilder

-0.40

genstein

-0.40

 vectorielles

-0.39

POSITIVE LOGITS

__':

0.64

Gro

0.57

 مشين

0.56

Gro

0.54

Personendaten

0.52

limite

0.50

限

0.50

 illustrationer

0.50

évaluateur

0.50

 conmigo

0.49

Activations Density 1.702%

references to specific individuals, organizations, or concepts associated with legal or technical topics

No Comments

No Known Activations