INDEX

Explanations

references to methods or approaches, particularly those indicated by the word "way"

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

OGND

-0.89

GEBURTSDATUM

-0.86

 Roskov

-0.84

 دیکھیے

-0.83

ItemBackground

-0.80

InvalidProtocol

-0.75

 يتيمه

-0.74

Personensuche

-0.72

ViewFeatures

-0.70

 actionMode

-0.70

POSITIVE LOGITS

to

0.64

 ways

0.57

how

0.57

way

0.56

 forward

0.49

 acercar

0.45

 besides

0.45

 pendekatan

0.45

 around

0.44

besides

0.43

Activations Density 0.081%

references to methods or approaches, particularly those indicated by the word "way"

No Comments

No Known Activations