INDEX

Explanations

terms related to specific geographical locations and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

scriptcase

-0.59

 Enugu

-0.56

 django

-0.55

siella

-0.51

 Pune

-0.51

 Telugu

-0.48

 Warwickshire

-0.48

 elegans

-0.47

佗

-0.47

gige

-0.47

POSITIVE LOGITS

 Arctic

1.28

 arctic

1.22

Arctic

1.15

 Alaska

1.05

arctic

1.05

 Alaskan

1.04

 Greenland

1.03

 tundra

1.03

 reindeer

0.98

Alaska

0.97

Activations Density 0.242%

terms related to specific geographical locations and communities

No Comments

No Known Activations