INDEX

Explanations

technical terms related to data storage and error control, especially focused on disk operations

oai_token-act-pair · gpt-3.5-turbo

terms related to disk storage and access

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yip

-0.83

pheus

-0.75

ean

-0.73

uyomi

-0.72

ndum

-0.72

terday

-0.71

ourgeois

-0.71

Kyr

-0.68

ADRA

-0.68

glers

-0.68

POSITIVE LOGITS

Disk

1.12

disk

1.05

 disks

1.04

 disk

1.03

 Disk

0.88

ussion

0.83

ettes

0.82

\/\/

0.82

ette

0.80

 shelves

0.75

Activations Density 0.010%

technical terms related to data storage and error control, especially focused on disk operations

terms related to disk storage and access

No Comments

No Known Activations