INDEX

Explanations

technical terms and references related to assays and programming structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

хьтан

-0.70

 AssemblyTitle

-0.70

ตร์

-0.68

حياته

-0.65

 فريبيس

-0.64

 Мексичка

-0.64

OGND

-0.64

-0.61

ossa

-0.60

 <>",

-0.60

POSITIVE LOGITS

IMO

0.58

 socio

0.56

 Toast

0.52

 toast

0.52

 polished

0.48

flo

0.48

WebMethod

0.47

 polish

0.47

toast

0.46

polished

0.46

Activations Density 3.389%

technical terms and references related to assays and programming structures

No Comments

No Known Activations