INDEX

Explanations

references to portions or segments within a context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Савезне

-0.73

Hochspringen

-0.71

eslint

-0.67

RuleContext

-0.64

marshaller

-0.64

 BoxFit

-0.63

 <=",

-0.63

NSMutable

-0.63

 متعلقه

-0.60

 arşivlendi

-0.60

POSITIVE LOGITS

 Britain

0.87

Britain

0.78

 Williams

0.77

 Americans

0.76

Williams

0.71

Americans

0.69

 BRITAIN

0.67

☆☆

0.63

williams

0.61

 Technologies

0.59

Activations Density 0.057%

references to portions or segments within a context

No Comments

No Known Activations