INDEX

Explanations

locations and institutional affiliations referenced in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ThroughAttribute

-0.57

 Chaco

-0.56

msgTypes

-0.55

 Haitian

-0.54

 Dubuque

-0.53

valdo

-0.53

Haiti

-0.52

 Juneau

-0.52

aragua

-0.52

 BufferedImage

-0.51

POSITIVE LOGITS

UK

2.50

 British

2.49

 Britain

2.40

 England

2.32

British

2.26

UK

2.20

 London

2.19

Britain

2.18

 Britons

2.09

 british

2.08

Activations Density 0.802%

locations and institutional affiliations referenced in a context

No Comments

No Known Activations