INDEX

Explanations

references to quantities or values followed by a word or phrase denoting a very large amount

oai_token-act-pair · gpt-3.5-turbo

phrases indicating high quantities or amounts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

illary

-0.81

 Lauder

-0.70

KE

-0.69

arium

-0.68

UE

-0.68

Ô

-0.67

****************

-0.67

ï¸

-0.66

UES

-0.64

ãĤ´

-0.63

POSITIVE LOGITS

loading

1.01

hang

1.00

drive

0.99

priced

0.97

lord

0.96

tones

0.90

whelming

0.89

population

0.89

haul

0.88

valued

0.88

Activations Density 0.103%

references to quantities or values followed by a word or phrase denoting a very large amount

phrases indicating high quantities or amounts

No Comments

No Known Activations