INDEX

Explanations

terms related to composition and combining elements or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 réfrig

-0.95

 Kars

-0.86

Demografía

-0.84

 Varela

-0.83

}],

-0.83

IsPostBack

-0.82

ociação

-0.81

الحياه

-0.81

 endforeach

-0.81

Khr

-0.78

POSITIVE LOGITS

 Compose

1.02

 compose

1.02

 compositions

0.94

 composed

0.92

Compose

0.92

composed

0.90

 composing

0.90

 Composition

0.88

Compos

0.87

 COMPOS

0.86

Activations Density 0.120%

terms related to composition and combining elements or structures

No Comments

No Known Activations