INDEX

Explanations

the name "George."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

adaptiveStyles

-0.64

 betweenstory

-0.60

printStackTrace

-0.53

 defStyleAttr

-0.53

 AttributeSet

-0.50

 ujednoznacz

-0.49

endsection

-0.48

⟭

-0.47

onViewCreated

-0.45

#+#

-0.43

POSITIVE LOGITS

dep

0.87

Geo

0.81

dep

0.81

Geo

0.79

George

0.77

 deploy

0.77

Dep

0.75

 George

0.74

Dep

0.73

 deployed

0.71

Activations Density 0.044%

the name "George."

No Comments

No Known Activations