INDEX

Explanations

roman numerals

oai_token-act-pair · gpt-3.5-turbo

linguistic elements and variations of words or phrases related to language

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CLASSIFIED

-0.74

 Enabled

-0.73

 relegation

-0.67

 Legacy

-0.64

 Achievements

-0.63

Loading

-0.63

Reloaded

-0.63

MPG

-0.62

 bankruptcy

-0.61

 Arduino

-0.61

POSITIVE LOGITS

Äĵ

1.47

É

1.41

Åį

1.36

Ç

1.29

Ä«

1.22

Äģ

1.21

Ã³

1.20

-,

1.19

-.

1.13

Ãº

1.11

Activations Density 0.159%

roman numerals

linguistic elements and variations of words or phrases related to language

No Comments

No Known Activations