INDEX

Explanations

technology-related words and phrases

oai_token-act-pair · gpt-3.5-turbo

names of notable individuals and their affiliations or accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

equality

-0.74

 uncertainties

-0.72

Monday

-0.69

WASHINGTON

-0.69

urden

-0.64

tnc

-0.63

ã

-0.62

asive

-0.62

wage

-0.62

Accept

-0.61

POSITIVE LOGITS

 incidentally

1.16

 infamous

1.13

 famously

1.12

 controvers

1.04

 renamed

1.02

 predecessor

1.01

 defunct

1.01

 precursor

1.00

 later

0.99

 famous

0.99

Activations Density 0.629%

technology-related words and phrases

names of notable individuals and their affiliations or accomplishments

No Comments

No Known Activations