INDEX

Explanations

terms related to geographical locations or coordinates

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

SpringRunner

-0.51

 Handsome

-0.46

 okuyayım

-0.42

 وا

-0.42

 Palme

-0.42

肇

-0.41

 prin

-0.41

อัน

-0.41

 épis

-0.40

äng

-0.39

POSITIVE LOGITS

Location

2.06

 Location

1.82

 location

1.51

 LOCATION

1.45

location

1.38

LOCATION

1.37

 Locations

1.36

Locations

1.22

getLocation

1.20

findpost

1.16

Activations Density 0.025%

terms related to geographical locations or coordinates

No Comments

No Known Activations