INDEX

Explanations

technical or coding-related terms and symbols

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

TagMode

-0.70

 invokingState

-0.61

 Савезне

-0.61

Eſ

-0.54

ьаж

-0.52

 occaf

-0.51

ReusableCell

-0.51

StructEnd

-0.50

Jeografia

-0.50

 betweenstory

-0.49

POSITIVE LOGITS

<?

0.46

 médec

0.35

 genannten

0.35

īdz

0.32

 porte

0.32

TabIndex

0.31

 malang

0.30

 SCORE

0.30

VERTIS

0.30

BorderSize

0.30

Activations Density 2.573%

technical or coding-related terms and symbols

No Comments

No Known Activations