INDEX

Explanations

references to encoding formats, specifically UTF

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

 lenker

-0.67

Enciclopedia

-0.67

Expedia

-0.64

SourceChecksum

-0.63

 Hacienda

-0.59

ultor

-0.58

RegressionTest

-0.57

ContentAlignment

-0.56

 Haci

-0.55

wpi

-0.53

POSITIVE LOGITS

葩

0.65

ãy

0.65

DeleteBehavior

0.64

DataSetChanged

0.61

niająca

0.59

 moderne

0.59

 Acht

0.59

FontOfSize

0.58

 StatefulWidget

0.58

utf

0.57

Activations Density 0.075%

references to encoding formats, specifically UTF

No Comments

No Known Activations