INDEX

Explanations

names of entities, particularly people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 StatelessWidget

-0.76

ұ

-0.65

puh

-0.63

datagrid

-0.63

 pattes

-0.62

 Zeller

-0.61

 riuscito

-0.60

Fris

-0.60

XB

-0.59

 Padma

-0.59

POSITIVE LOGITS

kespea

1.01

Gibbs

0.87

 surla

0.85

quelize

0.84

 Elliott

0.83

 Gibbs

0.82

;->

0.80

Elliott

0.76

mhz

0.76

mushroom

0.75

Activations Density 1.210%

names of entities, particularly people and organizations

No Comments

No Known Activations