INDEX

Explanations

words related to technology and companies, as well as names of specific technological devices and software

oai_token-act-pair · gpt-3.5-turbo

keywords related to specific brands or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

————————

-0.91

daq

-0.78

 Cosponsors

-0.73

DAQ

-0.68

itional

-0.68

eways

-0.67

MIC

-0.67

etter

-0.66

 visitation

-0.66

Reviewer

-0.65

POSITIVE LOGITS

uate

1.00

Ľ

0.97

ures

0.95

Ļ

0.90

uates

0.89

rates

0.83

uffs

0.81

ript

0.81

uated

0.81

uracy

0.78

Activations Density 0.084%

words related to technology and companies, as well as names of specific technological devices and software

keywords related to specific brands or products

No Comments

No Known Activations