INDEX

Explanations

terms related to optional features and variability

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

 typelib

-0.65

+#+

-0.65

EndInit

-0.57

 createState

-0.54

########.

-0.53

 WaitForSeconds

-0.52

posedge

-0.49

AsUp

-0.48

extAlignment

-0.47

 مشين

-0.47

POSITIVE LOGITS

 positioning

0.50

 intervention

0.48

 alternatively

0.47

aim

0.44

 spouse

0.43

 Argu

0.43

 garantia

0.42

ses

0.41

 partenza

0.41

 antemano

0.41

Activations Density 0.239%

terms related to optional features and variability

No Comments

No Known Activations