INDEX

Explanations

technical jargon related to robotics and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 detaljer

-0.59

новништво

-0.54

esistenza

-0.52

writeFieldEnd

-0.51

istle

-0.50

oherty

-0.48

 âgé

-0.48

 Stack

-0.48

skjaer

-0.47

 moks

-0.46

POSITIVE LOGITS

(!__

0.60

DeleteBehavior

0.58

SaveChangesAsync

0.57

Geplaatst

0.57

SequentialGroup

0.56

Initializable

0.53

bootstrapcdn

0.52

 Normdatei

0.51

发表于

0.51

stood

0.50

Activations Density 0.993%

technical jargon related to robotics and programming

No Comments

No Known Activations