INDEX

Explanations

references to specific applications and software features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 autorytatywna

-0.97

دانشنامهٔ

-0.80

はじめに

-0.80

 ModelExpression

-0.78

RegressionTest

-0.78

rungsseite

-0.77

 kaarangay

-0.76

Билгалдахарш

-0.76

 ویکی‌پدی

-0.76

MessageOf

-0.76

POSITIVE LOGITS

 Económica

0.58

’

0.54

 ftate

0.54

0.53

BeforeAll

0.50

álló

0.50

 itself

0.48

 blitt

0.48

 fhall

0.48

 stesso

0.46

Activations Density 0.375%

references to specific applications and software features

No Comments

No Known Activations