INDEX

Explanations

geographic location descriptors

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

IUrlHelper

-0.54

relser

-0.54

 itself

-0.53

✭✭

-0.53

([]

-0.53

amp

-0.52

FXMLLoader

-0.52

րջ

-0.49

ffé

-0.49

Hentet

-0.48

POSITIVE LOGITS

 AssemblyCompany

0.90

 southwest

0.72

 tdci

0.72

 myſelf

0.72

north

0.70

 whoſe

0.69

 leaſt

0.69

southwest

0.69

 northwest

0.67

 northerly

0.67

Activations Density 0.157%

geographic location descriptors

No Comments

No Known Activations