INDEX

Explanations

references to durations of time, specifically years and months

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

dbc

-0.72

 McClellan

-0.71

owulf

-0.71

 cherchés

-0.70

 pinulongan

-0.69

Investi

-0.69

 González

-0.69

Spurs

-0.68

ffiti

-0.68

 Duncan

-0.68

POSITIVE LOGITS

 year

1.89

 Year

1.72

 YEAR

1.68

year

1.62

Year

1.59

 years

1.55

YEAR

1.52

years

1.39

 Years

1.35

Years

1.31

Activations Density 0.121%

references to durations of time, specifically years and months

No Comments

No Known Activations