INDEX

Explanations

references to advanced concepts, techniques, or technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 المعيارى

-0.80

wußt

-0.78

nesia

-0.75

 giuri

-0.74

 FetchType

-0.74

eltzer

-0.73

 juridique

-0.73

 Spitfire

-0.72

AsStream

-0.72

 Wembley

-0.72

POSITIVE LOGITS

 advanced

2.04

 Advance

2.02

 advance

2.01

Advance

1.96

advanced

1.95

 Advanced

1.93

 advances

1.88

Advanced

1.86

 ADVANCE

1.84

advance

1.81

Activations Density 0.041%

references to advanced concepts, techniques, or technologies

No Comments

No Known Activations