INDEX

Explanations

machine code instructions and related technical terms

oai_token-act-pair · gpt-3.5-turbo

technical terms related to computer architecture and programming instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

soDeliveryDate

-1.05

hur

-0.83

arak

-0.80

ulhu

-0.76

podcast

-0.74

isner

-0.71

awaru

-0.71

ean

-0.71

ampunk

-0.70

anooga

-0.69

POSITIVE LOGITS

 pointer

1.15

addr

1.01

ptr

0.98

 bytes

0.98

 pointers

0.91

 buffer

0.88

disk

0.87

 overflow

0.87

 Width

0.87

 width

0.86

Activations Density 0.215%

machine code instructions and related technical terms

technical terms related to computer architecture and programming instructions

No Comments

No Known Activations