INDEX

Explanations

references to specific years and annual events

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

"year"

np_acts-logits-general · gemini-2.0-flash

year end, review, or period

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 McLeod

-0.45

 McKenzie

-0.43

 abzu

-0.43

 çı

-0.42

 Madsen

-0.40

envolvimento

-0.39

McL

-0.39

CWE

-0.38

 Lambeth

-0.38

McN

-0.38

POSITIVE LOGITS

Year

1.34

 Year

1.33

 year

1.27

 YEAR

1.25

YEAR

1.24

year

1.14

getYear

1.04

 Years

1.02

 years

1.00

 año

0.99

Activations Density 0.130%

references to specific years and annual events

"year"

year end, review, or period

No Comments

No Known Activations