INDEX

Explanations

technical terms related to computer programming and data manipulation

oai_token-act-pair · gpt-3.5-turbo

social media engagement indicators

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

âĵĺ

-0.50

Footnote

-0.47

conservancy

-0.46

tnc

-0.46

represented

-0.45

llah

-0.44

 thereto

-0.43

administ

-0.43

$.

-0.42

interrupted

-0.41

POSITIVE LOGITS

 Nurse

0.47

 Lists

0.47

???

0.41

 Xander

0.41

 Sets

0.41

 Shots

0.40

 Runs

0.40

 Movies

0.40

 Morty

0.40

Activations Density 6.549%

technical terms related to computer programming and data manipulation

social media engagement indicators

No Comments

No Known Activations