INDEX

Explanations

references to statistical or computational metrics in data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

berdayakan

-0.72

GEBURTSDATUM

-0.72

 mắn

-0.71

 useNavigate

-0.70

 lượt

-0.67

 Rapport

-0.67

Rapport

-0.66

 fevere

-0.63

Inflater

-0.63

verständlich

-0.62

POSITIVE LOGITS

 getC

0.95

getC

0.92

CCS

0.82

CQ

0.81

CBR

0.81

Cud

0.79

cupertino

0.79

CCC

0.79

Cs

0.77

CSC

0.77

Activations Density 2.329%

references to statistical or computational metrics in data analysis

No Comments

No Known Activations