INDEX

Explanations

references to the protein "Tre"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 tartalomajánló

-0.77

saraba

-0.73

 wicket

-0.66

 neceff

-0.65

 ſte

-0.64

 Púb

-0.63

 myſelf

-0.63

 fibrillation

-0.63

 Jefus

-0.62

 chords

-0.62

POSITIVE LOGITS

Tre

0.80

Tre

0.73

tre

0.73

 Mall

0.65

XmlAccessType

0.63

 tres

0.61

Ret

0.61

 mall

0.59

ագրություններ

0.59

ukone

0.57

Activations Density 0.093%

references to the protein "Tre"

No Comments

No Known Activations