INDEX

Explanations

references and attributions within the text

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

ByVersion

-0.44

IBarButtonItem

-0.42

 '\\;'

-0.41

 livs

-0.38

 contribución

-0.35

ch

-0.35

 cuantas

-0.35

 Longo

-0.34

 Gass

-0.34

 Frontera

-0.33

POSITIVE LOGITS

httphttps

0.69

########.

0.63

Erreferentziak

0.49

arote

0.49

˹

0.48

-------------</

0.47

WebElementEntity

0.47

fromnode

0.47

 Chwiliwch

0.46

ंदीखरीदारी

0.46

Activations Density 0.270%

references and attributions within the text

No Comments

No Known Activations