INDEX

Explanations

technical terms related to computer hardware, particularly focusing on chips

oai_token-act-pair · gpt-3.5-turbo

references to chips in technology contexts

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

axies

-0.69

æĢ

-0.68

 Alban

-0.67

 Stranger

-0.64

Vaj

-0.64

 Kazakh

-0.64

etheless

-0.64

ĺ

-0.62

 Brun

-0.61

ership

-0.61

POSITIVE LOGITS

otle

1.42

 chip

0.97

chip

0.96

board

0.92

 chips

0.84

washer

0.84

Chip

0.84

mun

0.82

pei

0.81

 implanted

0.78

Activations Density 0.006%

technical terms related to computer hardware, particularly focusing on chips

references to chips in technology contexts

No Comments

No Known Activations