INDEX

Explanations

the word "is" followed by a description or statement

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ares

-0.76

aired

-0.68

umbs

-0.67

è¦ļéĨĴ

-0.62

stocks

-0.61

enth

-0.61

iaries

-0.60

chairs

-0.58

olds

-0.58

eals

-0.58

POSITIVE LOGITS

 nothing

1.20

no

1.11

 plenty

1.06

 something

1.04

 nowhere

1.03

 ALWAYS

1.00

 ample

0.99

 always

0.99

 absolutely

0.98

 definitely

0.97

Activations Density 0.099%

the word "is" followed by a description or statement

No Comments

No Known Activations