INDEX

Explanations

sections labeled as "Conclusions" in the document

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

harvard

-0.46

wyr

-0.45

责任编辑

-0.44

 незавершена

-0.43

=#{

-0.43

co

-0.43

avra

-0.43

 player

-0.42

dalena

-0.42

miyorum

-0.42

POSITIVE LOGITS

 متعلقه

1.13

ंदीखरीदारी

0.99

rungsseite

0.92

:✨

0.90

parsedMessage

0.85

tvguidetime

0.84

GEBURTSDATUM

0.83

 مشين

0.81

 kasarigan

0.79

évaluateur

0.77

Activations Density 0.420%

sections labeled as "Conclusions" in the document

No Comments

No Known Activations