INDEX

Explanations

references to geographic locations specifically associated with "North."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 isolé

-0.51

 ciertamente

-0.49

 fieldName

-0.49

 rarement

-0.49

plak

-0.49

GIF

-0.48

 Mónica

-0.48

 pantallas

-0.47

scn

-0.47

ングラス

-0.47

POSITIVE LOGITS

 North

0.85

 worried

0.84

 NORTH

0.81

North

0.78

NA

0.71

findpost

0.71

 LoggerFactory

0.71

/**

0.71

 hydrostatic

0.70

ImageContext

0.70

Activations Density 0.073%

references to geographic locations specifically associated with "North."

No Comments

No Known Activations