INDEX

Explanations

terms related to future events or possibilities

oai_token-act-pair · gpt-3.5-turbo

references to the future

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

otto

-0.71

lua

-0.71

BuyableInstoreAndOnline

-0.66

onite

-0.66

Ing

-0.64

ema

-0.63

afort

-0.62

icial

-0.62

paio

-0.62

edIn

-0.62

POSITIVE LOGITS

 generations

1.00

 tense

0.94

 installments

0.90

 iterations

0.83

 editions

0.76

 horizon

0.70

ebin

0.68

isphere

0.68

 installment

0.67

 iteration

0.66

Activations Density 0.021%

terms related to future events or possibilities

references to the future

No Comments

No Known Activations