INDEX

Explanations

statistical data and numerical values

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

parsedMessage

-0.89

 surla

-0.88

 utafitiHapana

-0.87

]")]

-0.86

 queſta

-0.85

 kasarigan

-0.82

 ſche

-0.79



-0.79

 ſind

-0.78

 OFDb

-0.76

POSITIVE LOGITS

 estimado

0.44

 totalidad

0.43

 igualdad

0.42

 administrativo

0.42

 créditos

0.42

0.40

 liderança

0.40

 crédit

0.40

 crédito

0.40

Activations Density 0.288%

statistical data and numerical values

No Comments

No Known Activations