INDEX

Explanations

phrases that emphasize a personal recommendation or positive feedback

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

complexContent

-0.54

SequentialGroup

-0.51

 AssemblyCompany

-0.43

setContentView

-0.39

 копия

-0.39

ساز

-0.38

Geografie

-0.37

最快更新

-0.37

 tartalomajánló

-0.36

OGND

-0.35

POSITIVE LOGITS

featureID

0.66

期刊论文

0.57

 faults

0.52

 Einfluß

0.49

 items

0.49

 Meilleures

0.48

 elements

0.48

 components

0.47

 parts

0.47

 allies

0.46

Activations Density 1.635%

phrases that emphasize a personal recommendation or positive feedback

No Comments

No Known Activations