INDEX

Explanations

phrases indicating traditional practices or historical context

oai_token-act-pair · gpt-3.5-turbo

phrases related to traditional practices or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 cloud

-0.73

 Snapchat

-0.62

 land

-0.60

 neut

-0.59

cloud

-0.58

papers

-0.58

 books

-0.58

 Schwe

-0.58

 space

-0.58

isc

-0.58

POSITIVE LOGITS

terness

0.97

terday

0.96

alez

0.93

ulhu

0.90

ccording

0.89

utral

0.86

eteen

0.84

zsche

0.83

anyahu

0.80

kefeller

0.79

Activations Density 0.096%

phrases indicating traditional practices or historical context

phrases related to traditional practices or concepts

No Comments

No Known Activations