INDEX

Explanations

references to programming constructs or code-related keywords

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

verwijspagina

-0.83

tvguidetime

-0.73

 enfans

-0.71

Espèce

-0.69

 scolaires

-0.68

Collegamenti

-0.67

ollectionView

-0.63

 varandra

-0.62

 vectorielle

-0.61

 devenus

-0.60

POSITIVE LOGITS

 team

0.53

ณฑ

0.49

ImageContext

0.49

cial

0.48

 sauce

0.47

iod

0.45

წ

0.45

 benne

0.45

att

0.44

 abgerufen

0.44

Activations Density 0.760%

references to programming constructs or code-related keywords

No Comments

No Known Activations