INDEX

Explanations

content related to processes and improvements in various systems or mechanisms

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

Definitions

-0.46

 depositphotos

-0.40

 kingdoms

-0.40

rimid

-0.39

と思っています

-0.39

 områ

-0.37

 goddesses

-0.37

do

-0.36

 információk

-0.36

 associations

-0.36

POSITIVE LOGITS

 lifts

1.22

 wraps

1.21

 flips

1.18

 dumps

1.17

 mixes

1.16

 taps

1.16

 snaps

1.15

 sweeps

1.15

 feeds

1.14

 mounts

1.14

Activations Density 2.511%

content related to processes and improvements in various systems or mechanisms

No Comments

No Known Activations