INDEX

Explanations

mathematical expressions and notation related to convergence rates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.63

 Achter

-0.54

 Grat

-0.54

ⓘ

-0.54

BeginContext

-0.53

UnknownFieldSet

-0.53

 flyknit

-0.51

 cooler

-0.50

Mour

-0.48

 Surya

-0.48

POSITIVE LOGITS

 norms

0.69

 norm

0.68

 NORM

0.65

mybatisplus

0.63

infty

0.63

norms

0.62

 norme

0.60

norm

0.60

esgue

0.58

 normas

0.58

Activations Density 0.788%

mathematical expressions and notation related to convergence rates

No Comments

No Known Activations