INDEX

Explanations

symbols and notation related to mathematical processes, specifically in the context of stochastic or Markov processes

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

ViewImports

-0.90

 autorytatywna

-0.85

 pinulongan

-0.77

 onlyOwner

-0.73

rungsseite

-0.68

 anthropologist

-0.68

ModelAdmin

-0.64

IGENCE

-0.64

 Chaldean

-0.63

 MainAxisSize

-0.62

POSITIVE LOGITS

 JADX

0.52

Sus

0.47

เด

0.45

 sole

0.43

 kasarigan

0.43

Nullable

0.42

Sus

0.41

óch

0.41

 tanggal

0.41

biam

0.41

Activations Density 0.457%

symbols and notation related to mathematical processes, specifically in the context of stochastic or Markov processes

No Comments

No Known Activations