INDEX

Explanations

terms related to licensing and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Jeografia

-0.54

getSeconds

-0.46

engertian

-0.46

roek

-0.45

 chofe

-0.45

Gemeinden

-0.43

 ValueError

-0.43

 Newtonsoft

-0.43

pompa

-0.41

Radiant

-0.41

POSITIVE LOGITS

RenderAtEndOf

0.91

tagHelperRunner

0.81

AutoScaleMode

0.79

addContainerGap

0.77

存于互联网档案馆

0.74

AddTagHelper

0.71

EndContext

0.71

IUrlHelper

0.69

Carriera

0.68

SequentialGroup

0.67

Activations Density 0.002%

terms related to licensing and governance

No Comments

No Known Activations

terms related to licensing and governance

No Comments

No Known Activations