INDEX

Explanations

expressions of subjective opinions and evaluations

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

AndEndTag

-0.70

 ComVisible

-0.70

Diweddarwch

-0.66

 Italijanski

-0.66

afficheront

-0.66

SBATCH

-0.64

autoreleasepool

-0.64

 AspNetCore

-0.63

 Fibre

-0.63

setopt

-0.63

POSITIVE LOGITS

 rzecz

0.46

archiviato

0.45

 spoken

0.45

 powiedzieć

0.44

 لئے

0.41

 tegens

0.41

jsii

0.40

プーン

0.39

 seolah

0.39

 situazioni

0.39

Activations Density 0.470%

expressions of subjective opinions and evaluations

No Comments

No Known Activations