INDEX

Explanations

terms related to programming or configuration settings

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

RegressionTest

-0.89

 initComponents

-0.85

InjectAttribute

-0.84

parsedMessage

-0.84

TagMode

-0.83

WithIOException

-0.83

+#+#

-0.80

InitVars

-0.80

EndInit

-0.79

 ModelExpression

-0.77

POSITIVE LOGITS

<eos>

0.41

 Crédito

0.37

’

0.34

↵

0.32

 have

0.32

èdent

0.31

0.30

0.29

Activations Density 0.237%

terms related to programming or configuration settings

No Comments

No Known Activations