INDEX

Explanations

terms related to computer processing units (CPUs)

oai_token-act-pair · gpt-3.5-turbo

mentions of CPUs and related terminology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

reek

-0.90

zag

-0.75

erville

-0.73

arov

-0.72

red

-0.72

 Faust

-0.72

selves

-0.69

henko

-0.68

 Yanuk

-0.67

 Kremlin

-0.67

POSITIVE LOGITS

PDATE

1.10

 CPUs

0.94

 cores

0.86

CPU

0.85

 overcl

0.83

 architectures

0.81

cpu

0.81

 utilization

0.80

CPU

0.78

 emulation

0.78

Activations Density 0.005%

terms related to computer processing units (CPUs)

mentions of CPUs and related terminology

No Comments

No Known Activations