INDEX

Explanations

phrases containing non-English characters

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols that may indicate language-specific elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

anwhile

-0.82

 Montgomery

-0.78

 Boone

-0.75

 Appalach

-0.75

enegger

-0.74

 Pike

-0.73

 Clarks

-0.73

 Protector

-0.73

 Monsanto

-0.73

 Somerset

-0.72

POSITIVE LOGITS

¥µ

1.37

ħĭ

1.24

ĻĤ

1.23

Ľ

1.22

æ

1.20

¥ŀ

1.20

¹

1.19

Ĭ

1.19

¼

1.17

İ

1.16

Activations Density 0.004%

phrases containing non-English characters

special characters or symbols that may indicate language-specific elements

No Comments

No Known Activations