INDEX

Explanations

technical terms related to file systems and drive management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

UserScript

-0.72

 EconPapers

-0.58

ècie

-0.56

QMetaType

-0.54

 GeoNames

-0.54

CloseOperation

-0.53

EndContext

-0.52

 CURIAM

-0.51

UpdateCommand

-0.51

 Alquiler

-0.51

POSITIVE LOGITS

 disk

0.91

 storage

0.91

 drive

0.88

 drives

0.87

 Storage

0.86

 Drives

0.86

Drive

0.85

 Drive

0.83

disk

0.82

 Disk

0.79

Activations Density 0.334%

technical terms related to file systems and drive management

No Comments

No Known Activations