INDEX

Explanations

references to specific characters or entities and their associated attributes in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ChildScrollView

-0.76

 Numerade

-0.69

WithIdentifier

-0.66

 مشين

-0.65

PointerException

-0.64

basicConfig

-0.63

riever

-0.63

::_('

-0.60

 становника

-0.60

withIdentifier

-0.59

POSITIVE LOGITS

 InputDecoration

0.44

 suite

0.43

 suit

0.40

 SUITE

0.39

 Suit

0.39

 Suits

0.38

 Suite

0.38

Suit

0.38

 плю

0.37

Zus

0.37

Activations Density 2.081%

references to specific characters or entities and their associated attributes in narratives

No Comments

No Known Activations