INDEX

Explanations

references to specific locations and organizations

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

UrlResolution

-0.66

urlencoded

-0.56

 Legendre

-0.56

 cdti

-0.56

生平

-0.53

انيا

-0.51

 getty

-0.50

SourceChecksum

-0.50

 Bengali

-0.50

 Indias

-0.49

POSITIVE LOGITS

 Malta

0.95

Malta

0.92

 Maltese

0.86

ċ

0.69

ġ

0.66

 Vella

0.65

ħ

0.65

Ħ

0.61

0.60

 malta

0.56

Activations Density 0.014%

references to specific locations and organizations

No Comments

No Known Activations

references to specific locations and organizations

No Comments

No Known Activations