INDEX

Explanations

references to specific locations and community identifiers

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



-0.56

 Rukh

-0.54

 Administrativna

-0.54

-0.53

➯

-0.52

getDoctrine

-0.52

ſelves

-0.51

 ویکی‌پدی

-0.50

ArgumentParser

-0.49

 iprot

-0.48

POSITIVE LOGITS

setContentView

0.42

TemporalType

0.41

PREFERRED

0.40

 useStyles

0.38

TabIndex

0.36

 acompaña

0.35

 inmediato

0.33

UVWXYZ

0.33

מבר

0.32

 schlecht

0.31

Activations Density 0.070%

references to specific locations and community identifiers

No Comments

No Known Activations