INDEX

Explanations

references to theater and drama

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 تضيفلها

-0.86

gnore

-0.71

 onCancelled

-0.69

 mijne

-0.68

 Catan

-0.65

 licorne

-0.63

 getItemCount

-0.63

})));

-0.62

 ekolog

-0.61

 Alcott

-0.61

POSITIVE LOGITS

 theater

2.65

 theatre

2.58

 Theater

2.41

 Theatre

2.36

theater

2.20

theatre

2.20

Theater

2.17

Theatre

2.17

 theatres

2.03

 theaters

2.03

Activations Density 0.070%

references to theater and drama

No Comments

No Known Activations