INDEX

Explanations

instances of the word "in" and its context in looping structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

 havi

-0.46

↵

-0.41

Edy

-0.41

-0.40

بو

-0.40

-0.39

 Niki

-0.39

'#'

-0.39

ifoli

-0.38

zd

-0.37

POSITIVE LOGITS

}")]

1.12

ⓧ

1.07

 EconPapers

1.00

Vidite

0.96

saraba

0.93

//

0.92

 autorytatywna

0.90

migrationBuilder

0.89

 AssemblyTitle

0.88

'],

0.87

Activations Density 0.044%

instances of the word "in" and its context in looping structures

No Comments

No Known Activations