INDEX

Explanations

instances of the word "round" and related shapes or configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

cr

-0.51

cer

-0.50

 Tele

-0.50

mis

-0.49

jer

-0.48

Bec

-0.47

 justification

-0.47

mal

-0.46

los

-0.46

McC

-0.45

POSITIVE LOGITS

 disambiguazione

0.64

across

0.64

 Erscheinung

0.63

 Houſe

0.63

neſs

0.62

transQ

0.61

 capucha

0.61

Rounds

0.60

 cueva

0.60

 bahía

0.60

Activations Density 0.261%

instances of the word "round" and related shapes or configurations

No Comments

No Known Activations