INDEX

Explanations

elements related to structured data formats and alignments in mathematical or programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

rungen

-0.51

 possible

-0.51

tfrac

-0.51

tagne

-0.50

("</

-0.49

ومت

-0.49

bleshooting

-0.49

PREDICT

-0.49

PropertyChanging

-0.48

 Montagne

-0.48

POSITIVE LOGITS

StoryboardSegue

0.82

 فريبيس

0.71

Hentet

0.71

 للاسماء

0.70

isContained

0.59

Personensuche

0.55

商品説明

0.54

 distanciation

0.50

ıllı

0.48

 magasiner

0.48

Activations Density 0.005%

elements related to structured data formats and alignments in mathematical or programming contexts

No Comments

No Known Activations