INDEX

Explanations

elements related to claims, consequences, and social structures in contexts of authority and evaluation

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

styleType

-0.72

TestingModule

-0.66

httphttps

-0.66

 незавершена

-0.66

HostException

-0.64

 AssemblyCompany

-0.64

writeFieldEnd

-0.64

ItemBackground

-0.63

actéristi

-0.61

featureID

-0.61

POSITIVE LOGITS

 ease

0.35

 before

0.31

 avoid

0.31

...

0.30

als

0.30

gu

0.30

 Before

0.30

cap

0.30

 famili

0.29

ism

0.29

Activations Density 0.679%

elements related to claims, consequences, and social structures in contexts of authority and evaluation

No Comments

No Known Activations