INDEX

Explanations

specific geographical locations, scientific terms, and names of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Monument

-0.71

])){

-0.69

 Monument

-0.68

 Judson

-0.67

 Seis

-0.66

 Manas

-0.65

 Xanth

-0.64

 Gele

-0.63

bif

-0.63

─

-0.63

POSITIVE LOGITS

 Martel

0.93

 Frey

0.78

Pipes

0.77

 Dragons

0.76

 Ricci

0.74

 dragon

0.73

 Dragon

0.72

 koop

0.72

MeasureSpec

0.71

 Hamas

0.70

Activations Density 2.681%

specific geographical locations, scientific terms, and names of people

No Comments

No Known Activations