INDEX

Explanations

place names and their historical affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Luís

-0.78

Ats

-0.78

mrow

-0.77

 Vish

-0.76

 Dodo

-0.74

 Mors

-0.74

<i>

-0.73

rud

-0.72

 Belich

-0.71

alanta

-0.71

POSITIVE LOGITS

 Bracken

0.82

..\..\

0.81

 stiefel

0.80

 propOrder

0.79

sitemap

0.74

Cyl

0.73

appren

0.73

 Dresden

0.73

 herren

0.73

 Gaines

0.72

Activations Density 2.144%

place names and their historical affiliations

No Comments

No Known Activations