INDEX

Explanations

references to strips in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

)}_

-0.92

Vidite

-0.85

 immobilier

-0.85

 rendus

-0.82

 blessé

-0.79

}}">

-0.78

 artistique

-0.78

 uska

-0.77

abestanden

-0.76

 genitori

-0.76

POSITIVE LOGITS

 strip

1.59

 STRIP

1.57

strip

1.52

 Strip

1.45

 strips

1.44

STRIP

1.41

 Strips

1.38

Strip

1.38

 stripping

1.20

strips

1.20

Activations Density 0.023%

references to strips in various contexts

No Comments

No Known Activations