INDEX

Explanations

electronics and technology-related terms

oai_token-act-pair · gpt-3.5-turbo

words and names related to technology and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

taboola

-0.72

 thereof

-0.70

 considerable

-0.68

.,"

-0.67

 plausible

-0.66

 elaborate

-0.65

 prompting

-0.65

.),

-0.64

 concerned

-0.64

 whom

-0.64

POSITIVE LOGITS

 Profile

1.15

 Releases

1.09

 Presents

1.06

 Newsletter

1.03

 Picks

1.02

 Forums

1.01

 Tips

1.00

 Basics

0.99

 Logo

0.99

 Announce

0.98

Activations Density 0.433%

electronics and technology-related terms

words and names related to technology and products

No Comments

No Known Activations