INDEX

Explanations

phrases related to covering or encompassing a wide scope or range

oai_token-act-pair · gpt-3.5-turbo

terms related to complex relationships or interactions

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

 voic

-0.64

erick

-0.63

 partName

-0.63

imony

-0.63

 Wool

-0.62

 Victory

-0.62

 Guilty

-0.61

 Pell

-0.61

 testim

-0.61

 momentum

-0.60

POSITIVE LOGITS

assing

1.47

assed

1.42

adow

1.03

ages

0.95

cipline

0.95

aps

0.88

rowing

0.85

ading

0.84

apped

0.84

ivably

0.84

Activations Density 0.076%

phrases related to covering or encompassing a wide scope or range

terms related to complex relationships or interactions

No Comments

No Known Activations