INDEX

Explanations

the presence of special characters and specific formatting cues in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

UnitTesting

-0.52

 GenerationType

-0.50

 Wikispecies

-0.46

aarrggbb

-0.46

and

-0.45

łosi

-0.45

@[+][

-0.43

 segü

-0.42

])));

-0.42

 represented

-0.41

POSITIVE LOGITS

Portale

0.79

 متعلقه

0.77

rzost

0.70

 Roskov

0.70

 autorytatywna

0.67

onViewCreated

0.66

InjectMocks

0.64

참고

0.64

//

0.62

بوابة

0.58

Activations Density 0.969%

the presence of special characters and specific formatting cues in a text

No Comments

No Known Activations