INDEX

Explanations

structured data formats or code snippets related to programming

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

-0.48

ivably

-0.45

<?>>

-0.44

-0.42

-0.41

set

-0.41

きの

-0.40

<eos>

-0.40

POSITIVE LOGITS

 ProtoMessage

0.87

InjectAttribute

0.84

RTLD

0.80

 AssemblyCompany

0.75

 AssemblyProduct

0.75

 getItemId

0.74

 configureStore

0.73

✎

0.72

 CreateTagHelper

0.71

 onCreateView

0.70

Activations Density 0.380%

structured data formats or code snippets related to programming

No Comments

No Known Activations