INDEX

Explanations

words related to physical or mental energy levels

oai_token-act-pair · gpt-3.5-turbo

references to energy levels and vitality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ettings

-0.84

gery

-0.80

ãĥīãĥ©

-0.80

lihood

-0.78

 Settlement

-0.68

BuyableInstoreAndOnline

-0.67

 Doct

-0.66

kie

-0.66

geries

-0.63

cott

-0.63

POSITIVE LOGITS

 expended

0.83

 energy

0.80

 powering

0.80

 drinks

0.79

fulness

0.77

 Enhancement

0.75

 metabolism

0.74

 pulses

0.74

 ener

0.73

 energ

0.73

Activations Density 0.027%

words related to physical or mental energy levels

references to energy levels and vitality

No Comments

No Known Activations