INDEX

Explanations

instances of people walking in different scenarios

oai_token-act-pair · gpt-3.5-turbo

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

 contraction

-0.62

ãĥķãĤ©

-0.61

rish

-0.59

 wors

-0.59

Percent

-0.58

 Remastered

-0.58

ãĥĩãĤ£

-0.58

è¦ļéĨĴ

-0.57

vell

-0.57

amins

-0.56

POSITIVE LOGITS

 onto

1.32

 into

1.29

 INTO

1.17

 ashore

1.01

into

0.99

 downstairs

0.96

 past

0.96

 away

0.95

 onstage

0.94

 upstairs

0.89

Activations Density 0.174%

instances of people walking in different scenarios

No Comments

No Known Activations