INDEX

Explanations

technical terms related to software licensing and usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 onPostExecute

-0.83

 forgets

-0.60

 forgetting

-0.59

 forget

-0.58

>*/

-0.55

GeoNames

-0.54

 forgot

-0.54

oubliez

-0.53

setupUi

-0.53

 Skrill

-0.52

POSITIVE LOGITS

Pod

0.61

pod

0.58

bootstrapcdn

0.58

namespace

0.58

sizeCache

0.57

Pod

0.56

 apie

0.56

 CreateTagHelper

0.56

pod

0.55

POD

0.55

Activations Density 0.232%

technical terms related to software licensing and usage

No Comments

No Known Activations