INDEX

Explanations

terms and phrases related to chairs and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

lliant

-0.62

lankton

-0.61

írus

-0.59

internalType

-0.59

 obicei

-0.58

 artikke

-0.57

 odkazy

-0.57

">)</

-0.56

god

-0.56

cticut

-0.55

POSITIVE LOGITS

 chair

1.29

 Chair

1.24

 chairs

1.22

 Chairs

1.15

 CHAIR

1.15

 seat

1.11

Chair

1.10

 SEAT

1.08

chair

1.08

 seats

1.07

Activations Density 0.135%

terms and phrases related to chairs and their features

No Comments

No Known Activations