INDEX

Explanations

indicators of user input and customization in a digital context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

 transfieras

-0.75

 ſeveral

-0.65

 ſche

-0.63

 méri

-0.63

belong

-0.62

 fubject

-0.60

 quæ

-0.59

 kasarigan

-0.59

 appartiennent

-0.59

 Monfieur

-0.58

POSITIVE LOGITS

 selectively

0.50

 actively

0.50

 forcefully

0.46

 forcibly

0.45

 take

0.44

 make

0.42

 активно

0.42

 give

0.41

把

0.41

JoinColumn

0.40

Activations Density 0.003%

indicators of user input and customization in a digital context

No Comments

No Known Activations