INDEX

Explanations

references to clothing or suits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Drummond

-0.83

 Morgan

-0.66

 Edelman

-0.65

Datuak

-0.64

 kern

-0.63

 réflex

-0.63

ctrica

-0.63

Bry

-0.62

 CLOCK

-0.61

 Carnegie

-0.61

POSITIVE LOGITS

Su

1.30

Su

1.30

SU

1.24

 Suit

1.22

Suits

1.21

suit

1.17

Suit

1.14

 suit

1.13

 suits

1.13

 Suarez

1.11

Activations Density 0.072%

references to clothing or suits

No Comments

No Known Activations