INDEX

Explanations

phrases or sentences comparing an amount or level of something

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 antioxid

-0.61

 respir

-0.57

 sabot

-0.57

 unlaw

-0.56

ASED

-0.56

 orchestr

-0.54

 Making

-0.52

 hereby

-0.52

 Mushroom

-0.52

 Realms

-0.50

POSITIVE LOGITS

phy

1.20

pired

1.16

ynchron

1.15

pires

1.15

piration

1.05

 much

1.04

ocial

0.99

pire

0.93

phalt

0.93

part

0.93

Activations Density 0.131%

phrases or sentences comparing an amount or level of something

No Comments

No Known Activations