INDEX

Explanations

statistical metrics and analysis relating to research findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Vidite

-0.52

öglich

-0.48

 trov

-0.48

ơn

-0.47

KindOfClass

-0.46

traceback

-0.46

女王

-0.45

Flavor

-0.43

 jadx

-0.43

 disambiguazione

-0.43

POSITIVE LOGITS

\{\\

0.86

ArgsConstructor

0.86

ChildScrollView

0.73

httphttps

0.72

interopRequire

0.71

getWriter

0.70

WEBPACK

0.66

WebVitals

0.65

awaiter

0.65

SBATCH

0.64

Activations Density 0.179%

statistical metrics and analysis relating to research findings

No Comments

No Known Activations