INDEX

Explanations

references to geographic locations and associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nakalista

-0.76

EndContext

-0.76

ViewImports

-0.71

 GetEnumerator

-0.70

+#+#

-0.61

 NgModule

-0.59

 FetchType

-0.59

TagMode

-0.55

 sûrement

-0.55

 sacré

-0.54

POSITIVE LOGITS

 chapter

0.75

 National

0.67

 Chamber

0.64

chapter

0.62

leg

0.61

 branch

0.61

 Chapter

0.61

 Human

0.59

mybatisplus

0.58

 Institute

0.58

Activations Density 0.251%

references to geographic locations and associated entities

No Comments

No Known Activations