INDEX

Explanations

references to grass and doors

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

хьтан

-0.59

ကိုးကား

-0.54

__':

-0.53

 الرياضيه

-0.47

adopt

-0.47

__':

-0.46

Personendaten

-0.45

🛳

-0.43

RectangleBorder

-0.43

TagMode

-0.42

POSITIVE LOGITS

 Grass

0.54

ScopeManager

0.53

uch

0.52

tes

0.51

Tim

0.50

 racial

0.50

dot

0.49

door

0.48

wide

0.48

Grass

0.46

Activations Density 0.171%

references to grass and doors

No Comments

No Known Activations