INDEX

Explanations

patterns related to numerical data and quantities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 otomatig

-1.31

SharedCtor

-1.26

SharedDtor

-1.10

SourceChecksum

-1.08

 ModelExpression

-1.06

 Roskov

-1.06

RegressionTest

-1.05

AutoModerator

-1.00

Попис

-0.98

 betweenstory

-0.97

POSITIVE LOGITS

“

0.56

‚¬

0.53

เ

0.52

0.51

“

0.51

нской

0.51

‘

0.50

 эк

0.50

Activations Density 0.054%

patterns related to numerical data and quantities

No Comments

No Known Activations