INDEX

Explanations

specific nouns and their related contexts, particularly in legal or procedural settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 فريبيس

-0.82

RegistryLite

-0.77

 بيها

-0.74

PyExc

-0.71

///</

-0.70

WebServlet

-0.67

SourceChecksum

-0.67

__':

-0.66

()?;

-0.66

__':

-0.64

POSITIVE LOGITS

Odds

0.88

 Ruins

0.86

 odds

0.86

OrderDetails

0.84

 Odds

0.82

 ruins

0.78

 Specs

0.77

lyrics

0.74

getSettings

0.73

 stats

0.72

Activations Density 0.798%

specific nouns and their related contexts, particularly in legal or procedural settings

No Comments

No Known Activations