INDEX

Explanations

entities related to geographical locations and notable individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Karlsruhe

-0.70

Picasso

-0.68

 Franti

-0.67

lorin

-0.65

 Racine

-0.63

 Henson

-0.63

wój

-0.63

ண்டும்

-0.62

rgba

-0.61

Спољашње

-0.61

POSITIVE LOGITS

 LIVER

0.84

 jSON

0.82

Ber

0.79

 Crosby

0.79

jména

0.79

 ExecuteAsync

0.79

 keç

0.77

 Pollack

0.76

 Kuli

0.76

cessite

0.75

Activations Density 0.743%

entities related to geographical locations and notable individuals

No Comments

No Known Activations