INDEX

Explanations

scientific terminology and technical jargon related to measurements and analysis

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

DCM

-0.38

 Domino

-0.38

BZ

-0.37

Domino

-0.36

Gap

-0.35

Iris

-0.35

rrggbb

-0.35

seg

-0.34

Gap

-0.34

BP

-0.34

POSITIVE LOGITS

 Audiodateien

0.53

ValueGeneration

0.51

 discriminación

0.50

 oscuridad

0.49

 détect

0.48

 detection

0.47

 detección

0.46

 melhores

0.46

detection

0.46

 lembut

0.46

Activations Density 1.602%

scientific terminology and technical jargon related to measurements and analysis

No Comments

No Known Activations