INDEX

Explanations

references to experiences and their qualitative aspects

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

zugehen

-0.76

betical

-0.75

 dõi

-0.74

)_/¯

-0.70

MatInputModule

-0.70

subsid

-0.66

шаго

-0.65

abz

-0.65

 abzu

-0.63

 RoHS

-0.63

POSITIVE LOGITS

 experience

2.27

 experiences

2.21

 Experience

2.02

 Experiences

2.02

Experience

1.95

 EXPERIENCE

1.92

experience

1.90

EXPERIENCE

1.86

 experien

1.86

experiences

1.84

Activations Density 0.062%

references to experiences and their qualitative aspects

No Comments

No Known Activations