INDEX

Explanations

references to partitioning or grouping within data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 fidé

-1.14

 feroit

-1.13

 étoient

-1.12

 avoient

-1.09

 Monfieur

-1.08

 abstrait

-1.05

 auroit

-1.03

 pouvoit

-1.03

 ainfi

-1.02

 Majefty

-1.01

POSITIVE LOGITS

}^{+\

0.60

#+#

0.58

car

0.54

homonymie

0.53

des

0.53

::::::::

0.51

 calm

0.51

Bibliographie

0.51

cal

0.50

Activations Density 0.720%

references to partitioning or grouping within data

No Comments

No Known Activations