INDEX

Explanations

numerical values and unit abbreviations commonly found in scientific research papers

oai_token-act-pair · gpt-3.5-turbo

structured scientific data and statistical presentations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ouver

-0.83

atche

-0.80

ammy

-0.70

lehem

-0.69

aturday

-0.68

illery

-0.68

 Tradable

-0.67

vil

-0.67

=-=-

-0.65

ivan

-0.65

POSITIVE LOGITS

 âĪ¼

1.19

âĪĴ

1.17

 âĪĴ

1.13

Î²

1.12

 Supplementary

1.04

âĢĲ

1.04

 âī¥

1.01

 (âĪĴ

1.00

 Â±

0.99

Figure

0.99

Activations Density 0.368%

numerical values and unit abbreviations commonly found in scientific research papers

structured scientific data and statistical presentations

No Comments

No Known Activations