INDEX

Explanations

mathematical notation and terms related to physics or advanced mathematics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

الإنجليزية

-0.81

 HasFactory

-0.69

CloseOperation

-0.68

homonymie

-0.64

 Rowe

-0.61

tabular

-0.61

IndentedString

-0.60

rowser

-0.60

archiviato

-0.60

OSSARY

-0.59

POSITIVE LOGITS

bf

2.93

BF

1.85

bf

1.64

BF

1.44

Bf

1.18

Bf

0.81

textbf

0.76

bm

0.67

udah

0.64

bfs

0.63

Activations Density 0.191%

mathematical notation and terms related to physics or advanced mathematics

No Comments

No Known Activations