INDEX

Explanations

bulleted lists or items listed with numbers

oai_token-act-pair · gpt-3.5-turbo

occurrences 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

independence

-0.74

iage

-0.65

 crim

-0.64

atics

-0.63

uma

-0.61

fal

-0.61

acial

-0.59

 shaved

-0.59

 cradle

-0.59

ammed

-0.59

POSITIVE LOGITS

 List

3.74

 Lists

2.57

List

2.54

list

2.47

 LIST

2.47

 list

2.27

 lists

2.00

LIST

1.90

lists

1.74

 listing

1.64

Activations Density 0.016%

bulleted lists or items listed with numbers

occurrences of the word "List" and its variations

No Comments

No Known Activations