INDEX

Explanations

phrases highlighting important concepts and comparisons in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

олові

-0.41

RegressionTest

-0.41

hyrchwyd

-0.40

 للاسماء

-0.37

featureID

-0.36

ウンサー

-0.35

MockMvc

-0.35

Élet

-0.35

 ویکی‌آمباردا

-0.34

lecular

-0.33

POSITIVE LOGITS

 independently

0.60

+#+

0.60

 independent

0.49

independent

0.48

 indipendente

0.47

 INDEPENDENT

0.47

 bağı

0.45

 независи

0.43

 independente

0.42

lovely

0.41

Activations Density 0.539%

phrases highlighting important concepts and comparisons in context

No Comments

No Known Activations