INDEX

Explanations

references to hard drives

oai_token-act-pair · gpt-3.5-turbo

terms related to storage devices, particularly hard drives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yip

-0.86

Kyr

-0.73

oria

-0.72

EY

-0.72

avia

-0.71

Gaw

-0.70

rav

-0.70

 Seym

-0.70

 parach

-0.70

rians

-0.68

POSITIVE LOGITS

Drive

0.88

 partitions

0.85

Upload

0.80

disk

0.78

 drives

0.76

 controller

0.75

 storage

0.74

Transfer

0.74

Letter

0.73

 overwrite

0.70

Activations Density 0.025%

references to hard drives

terms related to storage devices, particularly hard drives

No Comments

No Known Activations