INDEX

Explanations

patterns of text formatting

oai_token-act-pair · gpt-3.5-turbo

numerical values and ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Ukrain

-0.73

 Shinra

-0.67

 Hein

-0.63

 Stanton

-0.61

 Amir

-0.61

hement

-0.61

 Vanderbilt

-0.61

gans

-0.60

iji

-0.59

 Bridges

-0.59

POSITIVE LOGITS

Loading

1.37

RAW

1.18

rawdownloadcloneembedreportprint

0.95

Posted

0.88

 ancest

0.86

Series

0.84

Catalog

0.82

OUNT

0.81

Topic

0.80

Ü

0.79

Activations Density 0.282%

patterns of text formatting

numerical values and ratings

No Comments

No Known Activations