INDEX

Explanations

the term "list"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "list" and its variations

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

 Aber

-0.62

 life

-0.62

lat

-0.62

 Gore

-0.60

 Metallic

-0.59

 parchment

-0.59

 Wildcats

-0.59

DH

-0.58

 farm

-0.57

 newfound

-0.57

POSITIVE LOGITS

list

1.17

ening

0.93

witz

0.93

eners

0.91

lists

0.88

ener

0.87

ing

0.86

LIST

0.86

abet

0.85

erv

0.85

Activations Density 0.006%

the term "list"

instances of the word "list" and its variations

No Comments

No Known Activations