INDEX

Explanations

terms related to birational geometry and smoothness

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-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

 whoſe

-0.71

 leſs

-0.65

 faſt

-0.65

 neceſſ

-0.65

SBATCH

-0.64

 themſelves

-0.64

 itſelf

-0.63

 fhort

-0.63

 neceff

-0.62

 intest

-0.59

POSITIVE LOGITS

jsonwebtoken

0.63

TargetException

0.60

ImageContext

0.60

IndentedString

0.58

DockStyle

0.57

Indented

0.52

#+#

0.52

 रेटिंग

0.52

HandlerContext

0.51

 demografica

0.50

Activations Density 2.720%

terms related to birational geometry and smoothness

No Comments

No Known Activations