INDEX

Explanations

relationships between objects or ideas in a context

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

 Económica

-0.56

 desmotivaciones

-0.52

yfikacja

-0.51

 tempio

-0.50

 operacional

-0.50

 financeira

-0.49

 orologio

-0.48

 energético

-0.47

 recargable

-0.47

 artesanales

-0.47

POSITIVE LOGITS

dro

0.47

bl

0.44

 ModelExpression

0.40

httphttps

0.39

tel

0.39

 پی

0.38

SES

0.38

ust

0.38

 cont

0.38

PIE

0.38

Activations Density 0.574%

relationships between objects or ideas in a context

No Comments

No Known Activations