INDEX

Explanations

descriptions of product features and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 disambiguazione

-0.84

 يتيمه

-0.72

Portály

-0.69

RegistryLite

-0.69

RenderAtEndOf

-0.67

الحياه

-0.64

 Roskov

-0.63

SourceChecksum

-0.62

EnableWeb

-0.62

 فريبيس

-0.59

POSITIVE LOGITS

 equipped

0.73

 packed

0.64

 backed

0.63

 voorzien

0.61

 available

0.58

 designed

0.57

 sure

0.56

 packaged

0.55

 priced

0.53

 offered

0.53

Activations Density 0.200%

descriptions of product features and specifications

No Comments

No Known Activations